English
Related papers

Related papers: Compact Speech Translation Models via Discrete Spe…

200 papers

Transformers have been the dominant architecture for Speech Translation in recent years, achieving significant improvements in translation quality. Since speech signals are longer than their textual counterparts, and due to the quadratic…

Computation and Language · Computer Science 2023-03-15 Ioannis Tsiamas , Gerard I. Gállego , José A. R. Fonollosa , Marta R. Costa-jussà

Speech-to-text translation has many potential applications for low-resource languages, but the typical approach of cascading speech recognition with machine translation is often impossible, since the transcripts needed to train a speech…

Computation and Language · Computer Science 2018-06-19 Sameer Bansal , Herman Kamper , Karen Livescu , Adam Lopez , Sharon Goldwater

Speech signals are inherently complex as they encompass both global acoustic characteristics and local semantic information. However, in the task of target speech extraction, certain elements of global and local semantic information in the…

Sound · Computer Science 2024-08-27 Zhaoxi Mu , Xinyu Yang , Sining Sun , Qing Yang

Speculative Decoding has emerged as a popular technique for accelerating inference in Large Language Models. However, most existing approaches yield only modest improvements in production serving systems. Methods that achieve substantial…

Computation and Language · Computer Science 2026-01-08 Michele Marzollo , Jiawei Zhuang , Niklas Roemer , Niklas Zwingenberger , Lorenz K. Müller , Lukas Cavigelli

Thanks to the latest deep learning algorithms, silent speech interfaces (SSI) are now able to synthesize intelligible speech from articulatory movement data under certain conditions. However, the resulting models are rather…

The goal of voice conversion is to transform source speech into a target voice, keeping the content unchanged. In this paper, we focus on self-supervised representation learning for voice conversion. Specifically, we compare discrete and…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-09 Benjamin van Niekerk , Marc-André Carbonneau , Julian Zaïdi , Mathew Baas , Hugo Seuté , Herman Kamper

Although large foundation models pre-trained by self-supervised learning have achieved state-of-the-art performance in many tasks including automatic speech recognition (ASR), knowledge distillation (KD) is often required in practice to…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-21 Xiaoyu Yang , Qiujia Li , Chao Zhang , Philip C. Woodland

Self-supervised pre-trained speech models have strongly improved speech recognition, yet they are still sensitive to domain shifts and accented or atypical speech. Many of these models rely on quantisation or clustering to learn discrete…

Audio and Speech Processing · Electrical Eng. & Systems 2025-02-06 Jakob Poncelet , Hugo Van hamme

We present UTDUSS, the UTokyo-SaruLab system submitted to Interspeech2024 Speech Processing Using Discrete Speech Unit Challenge. The challenge focuses on using discrete speech unit learned from large speech corpora for some tasks. We…

Sound · Computer Science 2024-03-21 Wataru Nakata , Kazuki Yamauchi , Dong Yang , Hiroaki Hyodo , Yuki Saito

Direct speech-to-speech translation (S2ST) aims to convert speech from one language into another, and has demonstrated significant progress to date. Despite the recent success, current S2ST models still suffer from distinct degradation in…

Computation and Language · Computer Science 2023-05-25 Rongjie Huang , Huadai Liu , Xize Cheng , Yi Ren , Linjun Li , Zhenhui Ye , Jinzheng He , Lichao Zhang , Jinglin Liu , Xiang Yin , Zhou Zhao

End-to-end Speech Translation (ST) aims at translating the source language speech into target language text without generating the intermediate transcriptions. However, the training of end-to-end methods relies on parallel ST data, which…

Computation and Language · Computer Science 2022-10-19 Chen Wang , Yuchen Liu , Boxing Chen , Jiajun Zhang , Wei Luo , Zhongqiang Huang , Chengqing Zong

Self-supervised learning (SSL) of speech has shown impressive results in speech-related tasks, particularly in automatic speech recognition (ASR). While most methods employ the output of intermediate layers of the SSL model as real-valued…

Sound · Computer Science 2023-05-30 Xuankai Chang , Brian Yan , Yuya Fujita , Takashi Maekaku , Shinji Watanabe

In text classification tasks, fine tuning pretrained language models like BERT and GPT-3 yields competitive accuracy; however, both methods require pretraining on large text datasets. In contrast, general topic modeling methods possess the…

Computation and Language · Computer Science 2024-02-13 Weijie Xu , Xiaoyu Jiang , Jay Desai , Bin Han , Fuqin Yan , Francis Iannacci

Discrete speech representation learning has recently attracted increasing interest in both acoustic and semantic modeling. Existing approaches typically encode 16 kHz waveforms into discrete tokens at a rate of 25 or 50 tokens per second.…

Computation and Language · Computer Science 2025-09-03 Jialong Zuo , Guangyan Zhang , Minghui Fang , Shengpeng Ji , Xiaoqi Jiao , Jingyu Li , Yiwen Guo , Zhou Zhao

The parallel advances in language modeling and speech representation learning have raised the prospect of learning language directly from speech without textual intermediates. This requires extracting semantic representations directly from…

This work presents self-supervised learning methods for developing monaural speaker-specific (i.e., personalized) speech enhancement models. While generalist models must broadly address many speakers, specialist models can adapt their…

Audio and Speech Processing · Electrical Eng. & Systems 2022-07-28 Aswin Sivaraman , Minje Kim

Recently, pioneer work finds that speech pre-trained models can solve full-stack speech processing tasks, because the model utilizes bottom layers to learn speaker-related information and top layers to encode content-related information.…

Audio and Speech Processing · Electrical Eng. & Systems 2021-12-17 Chengyi Wang , Yu Wu , Sanyuan Chen , Shujie Liu , Jinyu Li , Yao Qian , Zhenglu Yang

Speech language models (SpeechLMs) accept speech input and produce speech output, allowing for more natural human-computer interaction compared to text-based large language models (LLMs). Traditional approaches for developing SpeechLMs are…

Computation and Language · Computer Science 2024-12-03 Aohan Zeng , Zhengxiao Du , Mingdao Liu , Lei Zhang , Shengmin Jiang , Yuxiao Dong , Jie Tang

This work explores how self-supervised learning can be universally used to discover speaker-specific features towards enabling personalized speech enhancement models. We specifically address the few-shot learning scenario where access to…

Audio and Speech Processing · Electrical Eng. & Systems 2022-08-11 Aswin Sivaraman , Minje Kim

Speech-to-speech translation (S2ST) enables spoken communication between people talking in different languages. Despite a few studies on multilingual S2ST, their focus is the multilinguality on the source side, i.e., the translation from…

Computation and Language · Computer Science 2023-07-18 Hongyu Gong , Ning Dong , Sravya Popuri , Vedanuj Goswami , Ann Lee , Juan Pino