English
Related papers

Related papers: Curriculum Pre-training for End-to-End Speech Tran…

200 papers

This paper presents a novel framework to build a voice conversion (VC) system by learning from a text-to-speech (TTS) synthesis system, that is called TTS-VC transfer learning. We first develop a multi-speaker speech synthesis system with…

Audio and Speech Processing · Electrical Eng. & Systems 2021-01-07 Mingyang Zhang , Yi Zhou , Li Zhao , Haizhou Li

Code-switching (CS) refers to a linguistic phenomenon where a speaker uses different languages in an utterance or between alternating utterances. In this work, we study end-to-end (E2E) approaches to the Mandarin-English code-switching…

Computation and Language · Computer Science 2019-07-12 Zhiping Zeng , Yerbolat Khassanov , Van Tung Pham , Haihua Xu , Eng Siong Chng , Haizhou Li

Self-supervised learning (SSL) has grown in interest within the speech processing community, since it produces representations that are useful for many downstream tasks. SSL uses global and contextual methods to produce robust…

Audio and Speech Processing · Electrical Eng. & Systems 2024-11-08 Subrina Sultana , Donald S. Williamson

Although end-to-end text-to-speech (TTS) models such as Tacotron have shown excellent results, they typically require a sizable set of high-quality <text, audio> pairs for training, which are expensive to collect. In this paper, we propose…

Computation and Language · Computer Science 2018-08-31 Yu-An Chung , Yuxuan Wang , Wei-Ning Hsu , Yu Zhang , RJ Skerry-Ryan

With the massive developments of end-to-end (E2E) neural networks, recent years have witnessed unprecedented breakthroughs in automatic speech recognition (ASR). However, the codeswitching phenomenon remains a major obstacle that hinders…

Computation and Language · Computer Science 2024-02-28 Tzu-Ting Yang , Hsin-Wei Wang , Yi-Cheng Wang , Chi-Han Lin , Berlin Chen

In this work we focus on transferring supervision signals of natural language generation (NLG) tasks between multiple languages. We propose to pretrain the encoder and the decoder of a sequence-to-sequence model under both monolingual and…

Computation and Language · Computer Science 2019-11-25 Zewen Chi , Li Dong , Furu Wei , Wenhui Wang , Xian-Ling Mao , Heyan Huang

We report on adaptation of multilingual end-to-end speech recognition models trained on as many as 100 languages. Our findings shed light on the relative importance of similarity between the target and pretraining languages along the…

Computation and Language · Computer Science 2019-04-05 Oliver Adams , Matthew Wiesner , Shinji Watanabe , David Yarowsky

Recently, there has been growing interest in multi-speaker speech recognition, where the utterances of multiple speakers are recognized from their mixture. Promising techniques have been proposed for this task, but earlier works have…

Sound · Computer Science 2018-05-16 Hiroshi Seki , Takaaki Hori , Shinji Watanabe , Jonathan Le Roux , John R. Hershey

Pretraining and multitask learning are widely used to improve the speech to text translation performance. In this study, we are interested in training a speech to text translation model along with an auxiliary text to text translation task.…

Computation and Language · Computer Science 2021-07-14 Yun Tang , Juan Pino , Xian Li , Changhan Wang , Dmitriy Genzel

Multilingual sentence encoders (MSEs) are commonly obtained by training multilingual language models to map sentences from different languages into a shared semantic space. As such, they are subject to curse of multilinguality, a loss of…

Computation and Language · Computer Science 2025-06-02 Yongxin Huang , Kexin Wang , Goran Glavaš , Iryna Gurevych

Simultaneous speech-to-text translation is widely useful in many scenarios. The conventional cascaded approach uses a pipeline of streaming ASR followed by simultaneous MT, but suffers from error propagation and extra latency. To alleviate…

Computation and Language · Computer Science 2021-06-15 Junkun Chen , Mingbo Ma , Renjie Zheng , Liang Huang

Disfluency detection is usually an intermediate step between an automatic speech recognition (ASR) system and a downstream task. By contrast, this paper aims to investigate the task of end-to-end speech recognition and disfluency removal.…

Audio and Speech Processing · Electrical Eng. & Systems 2020-09-30 Paria Jamshid Lou , Mark Johnson

Building speech recognizers in multiple languages typically involves replicating a monolingual training recipe for each language, or utilizing a multi-task learning approach where models for different languages have separate output labels…

Computation and Language · Computer Science 2017-11-08 Suyoun Kim , Michael L. Seltzer

In this paper, we employ Singular Value Canonical Correlation Analysis (SVCCA) to analyze representations learnt in a multilingual end-to-end speech translation model trained over 22 languages. SVCCA enables us to estimate representational…

Computation and Language · Computer Science 2023-11-01 Haoran Sun , Xiaohu Zhao , Yikun Lei , Shaolin Zhu , Deyi Xiong

When a channel model is not available, the end-to-end training of encoder and decoder on a fading noisy channel generally requires the repeated use of the channel and of a feedback link. An important limitation of the approach is that…

Signal Processing · Electrical Eng. & Systems 2021-10-22 Sangwoo Park , Osvaldo Simeone , Joonhyuk Kang

We explore training attention-based encoder-decoder ASR in low-resource settings. These models perform poorly when trained on small amounts of transcribed speech, in part because they depend on having sufficient target-side text to train…

Audio and Speech Processing · Electrical Eng. & Systems 2019-08-06 Matthew Wiesner , Adithya Renduchintala , Shinji Watanabe , Chunxi Liu , Najim Dehak , Sanjeev Khudanpur

Data-driven models achieve successful results in Speech Emotion Recognition (SER). However, these models, which are often based on general acoustic features or end-to-end approaches, show poor performance when the testing set has a…

Audio and Speech Processing · Electrical Eng. & Systems 2025-12-15 Duowei Tang , Peter Kuppens , Lucca Geurts , Toon van Waterschoot

Pre-trained encoder-only and sequence-to-sequence (seq2seq) models each have advantages, however training both model types from scratch is computationally expensive. We explore recipes to improve pre-training efficiency by initializing one…

Computation and Language · Computer Science 2023-06-16 Saleh Soltan , Andy Rosenbaum , Tobias Falke , Qin Lu , Anna Rumshisky , Wael Hamza

Creating universal speaker encoders which are robust for different acoustic and speech duration conditions is a big challenge today. According to our observations systems trained on short speech segments are optimal for short phrase speaker…

Sound · Computer Science 2022-10-31 Sergey Novoselov , Vladimir Volokhov , Galina Lavrentyeva

Speech translation (ST) aims to learn transformations from speech in the source language to the text in the target language. Previous works show that multitask learning improves the ST performance, in which the recognition decoder generates…

Computation and Language · Computer Science 2020-07-07 Shun-Po Chuang , Tzu-Wei Sung , Alexander H. Liu , Hung-yi Lee
‹ Prev 1 4 5 6 7 8 10 Next ›