Cascaded systems remain most reliable
Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs
https://arxiv.org/abs/2512.16378
Sara Papi, Javier Garcia Gilabert, Zachary Hopton, Vilém Zouhar, Carlos Escolano, Gerard I. Gállego, Jorge Iranzo-Sánchez, Ahrii Kim, Dominik Macháček, Patricia Schmidtova, Maike Züfle
As Large Language Models (LLMs) expand beyond text, integrating speech as a native modality has given rise to SpeechLLMs, which aim to translate spoken language directly, thereby bypassing traditional transcription-based pipelines. Whether this integration improves speech-to-text translation quality over established cascaded architectures, however, remains an open question. We present Hearing to Translate, the first comprehensive test suite rigorously benchmarking 5 state-of-the-art SpeechLLMs against 16 strong direct and cascade systems that couple leading speech foundation models (SFM), with multilingual LLMs. Our analysis spans 16 benchmarks, 13 language pairs, and 9 challenging conditions, including disfluent, noisy, and long-form speech. Across this extensive evaluation, we find that cascaded systems remain the most reliable overall, while current SpeechLLMs only match cascades in selected settings and SFMs lag behind both, highlighting that integrating an LLM, either within the model or in a pipeline, is essential for high-quality speech translation.
Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs
https://arxiv.org/abs/2512.16378
Sara Papi, Javier Garcia Gilabert, Zachary Hopton, Vilém Zouhar, Carlos Escolano, Gerard I. Gállego, Jorge Iranzo-Sánchez, Ahrii Kim, Dominik Macháček, Patricia Schmidtova, Maike Züfle
As Large Language Models (LLMs) expand beyond text, integrating speech as a native modality has given rise to SpeechLLMs, which aim to translate spoken language directly, thereby bypassing traditional transcription-based pipelines. Whether this integration improves speech-to-text translation quality over established cascaded architectures, however, remains an open question. We present Hearing to Translate, the first comprehensive test suite rigorously benchmarking 5 state-of-the-art SpeechLLMs against 16 strong direct and cascade systems that couple leading speech foundation models (SFM), with multilingual LLMs. Our analysis spans 16 benchmarks, 13 language pairs, and 9 challenging conditions, including disfluent, noisy, and long-form speech. Across this extensive evaluation, we find that cascaded systems remain the most reliable overall, while current SpeechLLMs only match cascades in selected settings and SFMs lag behind both, highlighting that integrating an LLM, either within the model or in a pipeline, is essential for high-quality speech translation.
arXiv.org
Hearing to Translate: The Effectiveness of Speech Modality...
As Large Language Models (LLMs) expand beyond text, integrating speech as a native modality has given rise to SpeechLLMs, which directly process spoken language and enable speech-to-text...
ASR-optimized noise cancellation becomes a hot topic, demonstrating the gap in ASR system training
https://ai-coustics.com/2025/11/20/quail-stt-asr-transcription/
another one
https://www.sanas.ai/blog/inside-sanas-asr-optimized-noise-cancellation-for-agentic-ai
https://ai-coustics.com/2025/11/20/quail-stt-asr-transcription/
another one
https://www.sanas.ai/blog/inside-sanas-asr-optimized-noise-cancellation-for-agentic-ai
Ai-Coustics
Meet Quail: Improving transcription in every condition | ai-coustics | Audio intelligence
Real-world audio breaks many STT systems. Quail is a speech enhancement model built to improve transcription accuracy across noisy environments.
NVIDIA just released Nemotron Speech ASR:
🤖0.6B streaming cache-aware transducer
📉low latency (down to 80ms)
📈high throughput (up to 900 concurrent streams on H100)
🎮adjustable latency-throughput-accuracy trade-off without re-training
🌎English ASR
🔗https://huggingface.co/nvidia/nemotron-speech-streaming-en-0.6b
🤖0.6B streaming cache-aware transducer
📉low latency (down to 80ms)
📈high throughput (up to 900 concurrent streams on H100)
🎮adjustable latency-throughput-accuracy trade-off without re-training
🌎English ASR
🔗https://huggingface.co/nvidia/nemotron-speech-streaming-en-0.6b
huggingface.co
nvidia/nemotron-speech-streaming-en-0.6b · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
LFM released
https://huggingface.co/LiquidAI/LFM2.5-Audio-1.5B
LFM2.5-Audio-1.5B is Liquid AI's updated end-to-end audio foundation model. Key improvements include a custom, LFM based audio detokenizer, llama.cpp compatible GGUFs for CPU inference, and better ASR and TTS performance.
LFM2.5-Audio is an end-to-end multimodal speech and text language model, and as such does not require separate ASR and TTS components. Designed with low latency and real time conversation in mind, at only 1.5 billion parameters LFM2.5-Audio enables seamless conversational interaction, achieving capabilities on par with much larger models. Our model consists of a pretrained LFM2.5 model as its multimodal backbone, along with a FastConformer based audio encoder to handle continuous audio inputs, and an RQ-transformer generating discrete tokens coupled with a lightweight audio detokenizer for audio output.
https://huggingface.co/LiquidAI/LFM2.5-Audio-1.5B
LFM2.5-Audio-1.5B is Liquid AI's updated end-to-end audio foundation model. Key improvements include a custom, LFM based audio detokenizer, llama.cpp compatible GGUFs for CPU inference, and better ASR and TTS performance.
LFM2.5-Audio is an end-to-end multimodal speech and text language model, and as such does not require separate ASR and TTS components. Designed with low latency and real time conversation in mind, at only 1.5 billion parameters LFM2.5-Audio enables seamless conversational interaction, achieving capabilities on par with much larger models. Our model consists of a pretrained LFM2.5 model as its multimodal backbone, along with a FastConformer based audio encoder to handle continuous audio inputs, and an RQ-transformer generating discrete tokens coupled with a lightweight audio detokenizer for audio output.
huggingface.co
LiquidAI/LFM2.5-Audio-1.5B · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Nice effort and dataset, Russian is not great somehow despite 27k hours training data
https://lemas-project.github.io/LEMAS-Project/
https://lemas-project.github.io/LEMAS-Project/
lemas-project.github.io
LEMAS Project Page
LEMAS: A 150K-Hour Large-scale Extensible Multilingual Audio Suite with Generative Speech Models
Good in-depth research. Codecs could be better with a simple changes
https://arxiv.org/abs/2512.20211
Code here
https://github.com/sizigi/AliasingFreeNeuralAudioSynthesis
Aliasing-Free Neural Audio Synthesis
Yicheng Gu, Junan Zhang, Chaoren Wang, Jerry Li, Zhizheng Wu, Lauri Juvela
Neural vocoders and codecs reconstruct waveforms from acoustic representations, which directly impact the audio quality. Among existing methods, upsampling-based time-domain models are superior in both inference speed and synthesis quality, achieving state-of-the-art performance. Still, despite their success in producing perceptually natural sound, their synthesis fidelity remains limited due to the aliasing artifacts brought by the inadequately designed model architectures. In particular, the unconstrained nonlinear activation generates an infinite number of harmonics that exceed the Nyquist frequency, resulting in ``folded-back'' aliasing artifacts. The widely used upsampling layer, ConvTranspose, copies the mirrored low-frequency parts to fill the empty high-frequency region, resulting in ``mirrored'' aliasing artifacts. Meanwhile, the combination of its inherent periodicity and the mirrored DC bias also brings ``tonal artifact,'' resulting in constant-frequency ringing. This paper aims to solve these issues from a signal processing perspective. Specifically, we apply oversampling and anti-derivative anti-aliasing to the activation function to obtain its anti-aliased form, and replace the problematic ConvTranspose layer with resampling to avoid the ``tonal artifact'' and eliminate aliased components. Based on our proposed anti-aliased modules, we introduce Pupu-Vocoder and Pupu-Codec, and release high-quality pre-trained checkpoints to facilitate audio generation research. We build a test signal benchmark to illustrate the effectiveness of the anti-aliased modules, and conduct experiments on speech, singing voice, music, and audio to validate our proposed models. Experimental results confirm that our lightweight Pupu-Vocoder and Pupu-Codec models can easily outperform existing systems on singing voice, music, and audio, while achieving comparable performance on speech.
https://arxiv.org/abs/2512.20211
Code here
https://github.com/sizigi/AliasingFreeNeuralAudioSynthesis
Aliasing-Free Neural Audio Synthesis
Yicheng Gu, Junan Zhang, Chaoren Wang, Jerry Li, Zhizheng Wu, Lauri Juvela
Neural vocoders and codecs reconstruct waveforms from acoustic representations, which directly impact the audio quality. Among existing methods, upsampling-based time-domain models are superior in both inference speed and synthesis quality, achieving state-of-the-art performance. Still, despite their success in producing perceptually natural sound, their synthesis fidelity remains limited due to the aliasing artifacts brought by the inadequately designed model architectures. In particular, the unconstrained nonlinear activation generates an infinite number of harmonics that exceed the Nyquist frequency, resulting in ``folded-back'' aliasing artifacts. The widely used upsampling layer, ConvTranspose, copies the mirrored low-frequency parts to fill the empty high-frequency region, resulting in ``mirrored'' aliasing artifacts. Meanwhile, the combination of its inherent periodicity and the mirrored DC bias also brings ``tonal artifact,'' resulting in constant-frequency ringing. This paper aims to solve these issues from a signal processing perspective. Specifically, we apply oversampling and anti-derivative anti-aliasing to the activation function to obtain its anti-aliased form, and replace the problematic ConvTranspose layer with resampling to avoid the ``tonal artifact'' and eliminate aliased components. Based on our proposed anti-aliased modules, we introduce Pupu-Vocoder and Pupu-Codec, and release high-quality pre-trained checkpoints to facilitate audio generation research. We build a test signal benchmark to illustrate the effectiveness of the anti-aliased modules, and conduct experiments on speech, singing voice, music, and audio to validate our proposed models. Experimental results confirm that our lightweight Pupu-Vocoder and Pupu-Codec models can easily outperform existing systems on singing voice, music, and audio, while achieving comparable performance on speech.
arXiv.org
Aliasing-Free Neural Audio Synthesis
Neural vocoders and codecs reconstruct waveforms from acoustic representations, which directly impact the audio quality. Among existing methods, upsampling-based time-domain models are superior in...
Interesting classification of events continuous like <singing>...</singing> and standalone like [cough]
https://huggingface.co/datasets/yfish/WESR-Bench
https://arxiv.org/abs/2601.04508
WESR: Scaling and Evaluating Word-level Event-Speech Recognition
Chenchen Yang, Kexin Huang, Liwei Fan, Qian Tu, Botian Jiang, Dong Zhang, Linqi Yin, Shimin Li, Zhaoye Fei, Qinyuan Cheng, Xipeng Qiu
Speech conveys not only linguistic information but also rich non-verbal vocal events such as laughing and crying. While semantic transcription is well-studied, the precise localization of non-verbal events remains a critical yet under-explored challenge. Current methods suffer from insufficient task definitions with limited category coverage and ambiguous temporal granularity. They also lack standardized evaluation frameworks, hindering the development of downstream applications. To bridge this gap, we first develop a refined taxonomy of 21 vocal events, with a new categorization into discrete (standalone) versus continuous (mixed with speech) types. Based on the refined taxonomy, we introduce WESR-Bench, an expert-annotated evaluation set (900+ utterances) with a novel position-aware protocol that disentangles ASR errors from event detection, enabling precise localization measurement for both discrete and continuous events. We also build a strong baseline by constructing a 1,700+ hour corpus, and train specialized models, surpassing both open-source audio-language models and commercial APIs while preserving ASR quality. We anticipate that WESR will serve as a foundational resource for future research in modeling rich, real-world auditory scenes.
https://huggingface.co/datasets/yfish/WESR-Bench
https://arxiv.org/abs/2601.04508
WESR: Scaling and Evaluating Word-level Event-Speech Recognition
Chenchen Yang, Kexin Huang, Liwei Fan, Qian Tu, Botian Jiang, Dong Zhang, Linqi Yin, Shimin Li, Zhaoye Fei, Qinyuan Cheng, Xipeng Qiu
Speech conveys not only linguistic information but also rich non-verbal vocal events such as laughing and crying. While semantic transcription is well-studied, the precise localization of non-verbal events remains a critical yet under-explored challenge. Current methods suffer from insufficient task definitions with limited category coverage and ambiguous temporal granularity. They also lack standardized evaluation frameworks, hindering the development of downstream applications. To bridge this gap, we first develop a refined taxonomy of 21 vocal events, with a new categorization into discrete (standalone) versus continuous (mixed with speech) types. Based on the refined taxonomy, we introduce WESR-Bench, an expert-annotated evaluation set (900+ utterances) with a novel position-aware protocol that disentangles ASR errors from event detection, enabling precise localization measurement for both discrete and continuous events. We also build a strong baseline by constructing a 1,700+ hour corpus, and train specialized models, surpassing both open-source audio-language models and commercial APIs while preserving ASR quality. We anticipate that WESR will serve as a foundational resource for future research in modeling rich, real-world auditory scenes.
huggingface.co
yfish/WESR-Bench · Datasets at Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
More Anime. At modern state of research it is harmful to segment audio on chunks
https://huggingface.co/datasets/OmniAICreator/ASMR-Archive-Processed
https://huggingface.co/datasets/OmniAICreator/ASMR-Archive-Processed
Japanese dataset for emotions with descriptions in natural language. Good development from very generic emotion labels and even more confusing emotion vectors
https://github.com/UEC-InabaLab/ETCDataset
https://github.com/UEC-InabaLab/ETCDataset
GitHub
GitHub - UEC-InabaLab/ETCDataset
Contribute to UEC-InabaLab/ETCDataset development by creating an account on GitHub.
Many releases recently, including qwen-tts and others. Another LLM
https://github.com/FlashLabs-AI-Corp/FlashLabs-Chroma
https://github.com/FlashLabs-AI-Corp/FlashLabs-Chroma
GitHub
GitHub - FlashLabs-AI-Corp/FlashLabs-Chroma: Worlds first open-source real-time end-to-end spoken dialogue model with personalized…
Worlds first open-source real-time end-to-end spoken dialogue model with personalized voice cloning. - FlashLabs-AI-Corp/FlashLabs-Chroma
Vibevoice finetune for European languages, good results compared to baseline
https://huggingface.co/kugelaudio/kugelaudio-0-open
https://huggingface.co/kugelaudio/kugelaudio-0-open
https://www.assemblyai.com/universal-3-pro new model by assembly ai, LLM based. Supposed to be free for February, so a good chance to test.
Assemblyai
Universal-3 Pro by AssemblyAI
Introducing Universal-3 Pro, a first of its kind promptable speech language model. Control transcription using natural language prompting and domain context.
Interesting effort from Shinji on phoneme recognition
https://huggingface.co/espnet/powsm
https://arxiv.org/abs/2510.24992
POWSM: A Phonetic Open Whisper-Style Speech Foundation Model
Chin-Jou Li, Kalvin Chang, Shikhar Bharadwaj, Eunjung Yeo, Kwanghee Choi, Jian Zhu, David Mortensen, Shinji Watanabe
Recent advances in spoken language processing have led to substantial progress in phonetic tasks such as automatic speech recognition (ASR), phone recognition (PR), grapheme-to-phoneme conversion (G2P), and phoneme-to-grapheme conversion (P2G). Despite their conceptual similarity, these tasks have largely been studied in isolation, each relying on task-specific architectures and datasets. In this paper, we introduce POWSM (Phonetic Open Whisper-style Speech Model), the first unified framework capable of jointly performing multiple phone-related tasks. POWSM enables seamless conversion between audio, text (graphemes), and phones, opening up new possibilities for universal and low-resource speech processing. Our model outperforms or matches specialized PR models of similar size (Wav2Vec2Phoneme and ZIPA) while jointly supporting G2P, P2G, and ASR. Our training data, code and models are released to foster open science.
https://huggingface.co/espnet/powsm
https://arxiv.org/abs/2510.24992
POWSM: A Phonetic Open Whisper-Style Speech Foundation Model
Chin-Jou Li, Kalvin Chang, Shikhar Bharadwaj, Eunjung Yeo, Kwanghee Choi, Jian Zhu, David Mortensen, Shinji Watanabe
Recent advances in spoken language processing have led to substantial progress in phonetic tasks such as automatic speech recognition (ASR), phone recognition (PR), grapheme-to-phoneme conversion (G2P), and phoneme-to-grapheme conversion (P2G). Despite their conceptual similarity, these tasks have largely been studied in isolation, each relying on task-specific architectures and datasets. In this paper, we introduce POWSM (Phonetic Open Whisper-style Speech Model), the first unified framework capable of jointly performing multiple phone-related tasks. POWSM enables seamless conversion between audio, text (graphemes), and phones, opening up new possibilities for universal and low-resource speech processing. Our model outperforms or matches specialized PR models of similar size (Wav2Vec2Phoneme and ZIPA) while jointly supporting G2P, P2G, and ASR. Our training data, code and models are released to foster open science.
huggingface.co
espnet/powsm · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Some great results in phone recognition, no code yet but probably it will appear soon
https://www.arxiv.org/abs/2602.01634
HuPER: A Human-Inspired Framework for Phonetic Perception
Chenxu Guo, Jiachen Lian, Yisi Liu, Baihe Huang, Shriyaa Narayanan, Cheol Jun Cho, Gopala Anumanchipalli
We propose HuPER, a human-inspired framework that models phonetic perception as adaptive inference over acoustic-phonetics evidence and linguistic knowledge. With only 100 hours of training data, HuPER achieves state-of-the-art phonetic error rates on five English benchmarks and strong zero-shot transfer to 95 unseen languages. HuPER is also the first framework to enable adaptive, multi-path phonetic perception under diverse acoustic conditions. All training data, models, and code are open-sourced. Code and demo avaliable at this https URL.
https://www.arxiv.org/abs/2602.01634
HuPER: A Human-Inspired Framework for Phonetic Perception
Chenxu Guo, Jiachen Lian, Yisi Liu, Baihe Huang, Shriyaa Narayanan, Cheol Jun Cho, Gopala Anumanchipalli
We propose HuPER, a human-inspired framework that models phonetic perception as adaptive inference over acoustic-phonetics evidence and linguistic knowledge. With only 100 hours of training data, HuPER achieves state-of-the-art phonetic error rates on five English benchmarks and strong zero-shot transfer to 95 unseen languages. HuPER is also the first framework to enable adaptive, multi-path phonetic perception under diverse acoustic conditions. All training data, models, and code are open-sourced. Code and demo avaliable at this https URL.
arXiv.org
HuPER: A Human-Inspired Framework for Phonetic Perception
We propose HuPER, a human-inspired framework that models phonetic perception as adaptive inference over acoustic-phonetics evidence and linguistic knowledge. With only 100 hours of training data,...
https://github.com/FireRedTeam/FireRedASR2S
Interesting things:
FireRedVAD 100+ languages, 20+ Chinese dialects/accents
FireRedLID 100+ languages, 20+ Chinese dialects/accents
FLEURS-VAD-102: We randomly selected ~100 audio files per language from FLEURS test set, resulting in 9,443 audio files with manually annotated binary VAD labels (speech=1, silence=0). This VAD testset will be open sourced (coming soon).
Interesting things:
FireRedVAD 100+ languages, 20+ Chinese dialects/accents
FireRedLID 100+ languages, 20+ Chinese dialects/accents
FLEURS-VAD-102: We randomly selected ~100 audio files per language from FLEURS test set, resulting in 9,443 audio files with manually annotated binary VAD labels (speech=1, silence=0). This VAD testset will be open sourced (coming soon).