English
Related papers

Related papers: MOSS-Audio-Tokenizer: Scaling Audio Tokenizers for…

200 papers

Self-supervised learning (SSL) proficiency in speech-related tasks has driven research into utilizing discrete tokens for speech tasks like recognition and translation, which offer lower storage requirements and great potential to employ…

Audio and Speech Processing · Electrical Eng. & Systems 2023-12-15 Yifan Yang , Feiyu Shen , Chenpeng Du , Ziyang Ma , Kai Yu , Daniel Povey , Xie Chen

Neural audio codecs, neural networks which compress a waveform into discrete tokens, play a crucial role in the recent development of audio generative models. State-of-the-art codecs rely on the end-to-end training of an autoencoder and a…

Sound · Computer Science 2025-03-26 Zineb Lahrichi , Gaëtan Hadjeres , Gael Richard , Geoffroy Peeters

This paper presents a simple method that allows to easily enhance textual pre-trained large language models with speech information, when fine-tuned for a specific classification task. A classical issue with the fusion of many embeddings…

Computation and Language · Computer Science 2026-04-07 Nicolas Calbucura , Jose Guillen , Valentin Barriere

Recent advances in Automatic Speech Recognition (ASR) have been largely fueled by massive speech corpora. However, extending coverage to diverse languages with limited resources remains a formidable challenge. This paper introduces Speech…

Computation and Language · Computer Science 2025-05-23 Tianduo Wang , Lu Xu , Wei Lu , Shanbo Cheng

The practical deployment of Audio-Visual Speech Recognition (AVSR) systems is fundamentally challenged by significant performance degradation in real-world environments, characterized by unpredictable acoustic noise and visual interference.…

Audio and Speech Processing · Electrical Eng. & Systems 2025-12-17 Sungnyun Kim

The conversion from text to speech relies on the accurate mapping from linguistic to acoustic symbol sequences, for which current practice employs recurrent statistical models like recurrent neural networks. Despite the good performance of…

Sound · Computer Science 2018-11-07 Santiago Pascual , Antonio Bonafonte , Joan Serrà

Recent advancements in text-to-speech (TTS) powered by language models have showcased remarkable capabilities in achieving naturalness and zero-shot voice cloning. Notably, the decoder-only transformer is the prominent architecture in this…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-12 Théodor Lemerle , Nicolas Obin , Axel Roebel

This paper proposes a direct text to speech translation system using discrete acoustic units. This framework employs text in different source languages as input to generate speech in the target language without the need for text…

Computation and Language · Computer Science 2023-09-15 Victoria Mingote , Pablo Gimeno , Luis Vicente , Sameer Khurana , Antoine Laurent , Jarod Duret

Large language models (LLMs) have significantly advanced audio processing through audio codecs that convert audio into discrete tokens, enabling the application of language modelling techniques to audio data. However, traditional codecs…

Sound · Computer Science 2024-12-02 Haohe Liu , Xuenan Xu , Yi Yuan , Mengyue Wu , Wenwu Wang , Mark D. Plumbley

Speech 'in-the-wild' is a handicap for speaker recognition systems due to the variability induced by real-life conditions, such as environmental noise and the emotional state of the speaker. Taking advantage of the principles of…

Audio and Speech Processing · Electrical Eng. & Systems 2022-05-17 Esther Rituerto-González , Carmen Peláez-Moreno

Neural end-to-end TTS can generate very high-quality synthesized speech, and even close to human recording within similar domain text. However, it performs unsatisfactory when scaling it to challenging test sets. One concern is that the…

Audio and Speech Processing · Electrical Eng. & Systems 2019-07-23 Yibin Zheng , Xi Wang , Lei He , Shifeng Pan , Frank K. Soong , Zhengqi Wen , Jianhua Tao

Foundation models are reshaping EEG analysis, yet an important problem of EEG tokenization remains a challenge. This paper presents TFM-Tokenizer, a novel tokenization framework that learns a vocabulary of time-frequency motifs from…

Machine Learning · Computer Science 2026-05-15 Jathurshan Pradeepkumar , Xihao Piao , Zheng Chen , Jimeng Sun

We extend the frameworks of Serialized Output Training (SOT) to address practical needs of both streaming and offline automatic speech recognition (ASR) applications. Our approach focuses on balancing latency and accuracy, catering to…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-18 Aswin Shanmugam Subramanian , Amit Das , Naoyuki Kanda , Jinyu Li , Xiaofei Wang , Yifan Gong

Noise reduction techniques based on deep learning have demonstrated impressive performance in enhancing the overall quality of recorded speech. While these approaches are highly performant, their application in audio engineering can be…

Sound · Computer Science 2023-10-18 Christian J. Steinmetz , Thomas Walther , Joshua D. Reiss

Automatic speech quality assessment aims to quantify subjective human perception of speech through computational models to reduce the need for labor-consuming manual evaluations. While models based on deep learning have achieved progress in…

Sound · Computer Science 2025-04-30 Zhicheng Lian , Lizhi Wang , Hua Huang

Neural audio codecs are initially introduced to compress audio data into compact codes to reduce transmission latency. Researchers recently discovered the potential of codecs as suitable tokenizers for converting continuous audio into…

Audio and Speech Processing · Electrical Eng. & Systems 2024-02-21 Haibin Wu , Xuanjun Chen , Yi-Cheng Lin , Kai-wei Chang , Ho-Lam Chung , Alexander H. Liu , Hung-yi Lee

Neural audio coding has emerged as a vivid research direction by promising good audio quality at very low bitrates unachievable by classical coding techniques. Here, end-to-end trainable autoencoder-like models represent the state of the…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-20 Andreas Brendel , Nicola Pia , Kishan Gupta , Lyonel Behringer , Guillaume Fuchs , Markus Multrus

Neural audio codecs provide promising acoustic features for speech synthesis, with representative streaming codecs like Mimi providing high-quality acoustic features for real-time Text-to-Speech (TTS) applications. However, Mimi's decoder,…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-29 Haibin Wu , Bach Viet Do , Naveen Suda , Julian Chan , Madhavan C R , Gene-Ping Yang , Yi-Chiao Wu , Naoyuki Kanda , Yossef Adi , Xin Lei , Yue Liu , Florian Metze , Yuzong Liu

Despite their fundamental role, it remains unclear what properties could make tokenizers more effective for generative modeling. We observe that modern generative models share a conceptually similar training objective -- reconstructing…

Computer Vision and Pattern Recognition · Computer Science 2026-02-17 Jiawei Yang , Tianhong Li , Lijie Fan , Yonglong Tian , Yue Wang

We study why continuous diffusion language models (DLMs) have lagged behind discrete diffusion approaches despite their appealing continuous generative dynamics. Under a controlled token--recovery study, we identify token rounding, the…

Computation and Language · Computer Science 2026-03-04 Junzhe Shen , Jieru Zhao , Ziwei He , Zhouhan Lin