English
Related papers

Related papers: STaR: Distilling Speech Temporal Relation for Ligh…

200 papers

Recent state-of-the-art approaches to summarization utilize large pre-trained Transformer models. Distilling these models to smaller student models has become critically important for practical use; however there are many different…

Computation and Language · Computer Science 2020-10-29 Sam Shleifer , Alexander M. Rush

Self-supervised learning (SSL) has revolutionized audio representations, yet models often remain domain-specific, focusing on either speech or non-speech tasks. In this work, we present Universal Speech and Audio Distillation (USAD), a…

Sound · Computer Science 2025-08-19 Heng-Jui Chang , Saurabhchand Bhati , James Glass , Alexander H. Liu

Autoregressive (AR) models with diffusion heads have recently achieved strong text-to-audio performance, yet their iterative decoding and multi-step sampling process introduce high-latency issues. To address this bottleneck, we propose a…

Direct speech translation (ST) has shown to be a complex task requiring knowledge transfer from its sub-tasks: automatic speech recognition (ASR) and machine translation (MT). For MT, one of the most promising techniques to transfer…

Computation and Language · Computer Science 2020-12-10 Marco Gaido , Mattia A. Di Gangi , Matteo Negri , Marco Turchi

Speaker representation learning is crucial for voice recognition systems, with recent advances in self-supervised approaches reducing dependency on labeled data. Current two-stage iterative frameworks, while effective, suffer from…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-03 Danwei Cai , Zexin Cai , Ze Li , Ming Li

Many text mining models are constructed by fine-tuning a large deep pre-trained language model (PLM) in downstream tasks. However, a significant challenge nowadays is maintaining performance when we use a lightweight model with limited…

Computation and Language · Computer Science 2023-10-23 Weifeng Jiang , Qianren Mao , Chenghua Lin , Jianxin Li , Ting Deng , Weiyi Yang , Zheng Wang

The rapid development of large-scale text-to-speech (TTS) models has led to significant advancements in modeling diverse speaker prosody and voices. However, these models often face issues such as slow inference speeds, reliance on complex…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-17 Yinghao Aaron Li , Xilin Jiang , Cong Han , Nima Mesgarani

Target speech separation is the process of filtering a certain speaker's voice out of speech mixtures according to the additional speaker identity information provided. Recent works have made considerable improvement by processing signals…

Sound · Computer Science 2021-09-28 Qingjian Lin , Lin Yang , Xuyang Wang , Luyuan Xie , Chen Jia , Junjie Wang

Speech separation has been successfully applied as a frontend processing module of conversation transcription systems thanks to its ability to handle overlapped speech and its flexibility to combine with downstream tasks such as automatic…

Audio and Speech Processing · Electrical Eng. & Systems 2021-07-06 Jian Wu , Zhuo Chen , Sanyuan Chen , Yu Wu , Takuya Yoshioka , Naoyuki Kanda , Shujie Liu , Jinyu Li

In this paper, we propose Stochastic Knowledge Distillation (SKD) to obtain compact BERT-style language model dubbed SKDBERT. In each iteration, SKD samples a teacher model from a pre-defined teacher ensemble, which consists of multiple…

Computation and Language · Computer Science 2022-11-30 Zixiang Ding , Guoqing Jiang , Shuai Zhang , Lin Guo , Wei Lin

Self-supervised learning (SSL) has emerged as a promising paradigm for learning flexible speech representations from unlabeled data. By designing pretext tasks that exploit statistical regularities, SSL models can capture useful…

Sound · Computer Science 2024-01-25 Yusuf Brima , Ulf Krumnack , Simone Pika , Gunther Heidemann

Self-supervised learning (SSL) on large-scale datasets like AudioSet has become the dominant paradigm for audio representation learning. While the continuous influx of new, unlabeled audio presents an opportunity to enrich these static…

Sound · Computer Science 2026-01-26 Yizhou Zhang , Yuan Gao , Wangjin Zhou , Zicheng Yuan , Keisuke Imoto , Tatsuya Kawahara

Self-supervised learning (SSL) has significantly advanced acoustic representation learning. However, most existing models are optimised for either speech or audio event understanding, resulting in a persistent gap between these two domains.…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-05 Xiaoyu Yang , Yifan Yang , Zengrui Jin , Ziyun Cui , Wen Wu , Baoxiang Li , Chao Zhang , Phil Woodland

End-to-end speech translation (ST) for conversation recordings involves several under-explored challenges such as speaker diarization (SD) without accurate word time stamps and handling of overlapping speech in a streaming fashion. In this…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-24 Mu Yang , Naoyuki Kanda , Xiaofei Wang , Junkun Chen , Peidong Wang , Jian Xue , Jinyu Li , Takuya Yoshioka

The automated classification of stuttered speech has significant implications for timely assessments providing assistance to speech language pathologists. Despite notable advancements in the field, the cases in which multiple disfluencies…

Sound · Computer Science 2025-02-27 Huma Ameer , Seemab Latif , Mehwish Fatima

Diffusion models can synthesize realistic co-speech video from audio for various applications, such as video creation and virtual agents. However, existing diffusion-based methods are slow due to numerous denoising steps and costly…

Computer Vision and Pattern Recognition · Computer Science 2025-10-06 Beijia Lu , Ziyi Chen , Jing Xiao , Jun-Yan Zhu

This work focuses on the efficiency of the knowledge distillation approach in generating a lightweight yet powerful BERT based model for natural language processing applications. After the model creation, we applied the resulting model,…

Computation and Language · Computer Science 2024-11-04 Ahmed Akib Jawad Karim , Kazi Hafiz Md. Asad , Md. Golam Rabiul Alam

Recent advancements in Self-Supervised Learning (SSL) have shown promising results in Speaker Verification (SV). However, narrowing the performance gap with supervised systems remains an ongoing challenge. Several studies have observed that…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-25 Victor Miara , Theo Lepage , Reda Dehak

Self-supervised learning (SSL) methods such as WavLM have shown promising speech separation (SS) results in small-scale simulation-based experiments. In this work, we extend the exploration of the SSL-based SS by massively scaling up both…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-29 Zhuo Chen , Naoyuki Kanda , Jian Wu , Yu Wu , Xiaofei Wang , Takuya Yoshioka , Jinyu Li , Sunit Sivasankaran , Sefik Emre Eskimez

Recently, self-supervised learning (SSL) from unlabelled speech data has gained increased attention in the automatic speech recognition (ASR) community. Typical SSL methods include autoregressive predictive coding (APC), Wav2vec2.0, and…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-02 Ruchao Fan , Yunzheng Zhu , Jinhan Wang , Abeer Alwan