English
Related papers

Related papers: Listen, Attend and Spell

200 papers

In this paper, we present a novel two-pass approach to unify streaming and non-streaming end-to-end (E2E) speech recognition in a single model. Our model adopts the hybrid CTC/attention architecture, in which the conformer layers in the…

Sound · Computer Science 2021-12-30 Binbin Zhang , Di Wu , Zhuoyuan Yao , Xiong Wang , Fan Yu , Chao Yang , Liyong Guo , Yaguang Hu , Lei Xie , Xin Lei

We introduce a text-to-speech(TTS) framework based on a neural transducer. We use discretized semantic tokens acquired from wav2vec2.0 embeddings, which makes it easy to adopt a neural transducer for the TTS framework enjoying its monotonic…

Audio and Speech Processing · Electrical Eng. & Systems 2023-11-09 Minchan Kim , Myeonghun Jeong , Byoung Jin Choi , Dongjune Lee , Nam Soo Kim

Normally, a system that translates speech into text consists of separate modules for speech recognition and text-to-text translation. Combining those tasks into a SpeechLLM promises to exploit paralinguistic information in the speech and to…

Computation and Language · Computer Science 2026-05-15 Titouan Parcollet , Shucong Zhang , Xianrui Zheng , Rogier C. van Dalen

This article surveys convolution-based models including convolutional neural networks (CNNs), Conformers, ResNets, and CRNNs-as speech signal processing models and provide their statistical backgrounds and speech recognition, speaker…

Sound · Computer Science 2024-12-02 Nirmal Joshua Kapu , Raghav Karan

End-to-end automatic speech recognition (ASR) commonly transcribes audio signals into sequences of characters while its performance is evaluated by measuring the word-error rate (WER). This suggests that predicting sequences of words…

Computation and Language · Computer Science 2018-12-07 Jan Kremer , Lasse Borgholt , Lars Maaløe

Speech Emotion Recognition (SER) task has known significant improvements over the last years with the advent of Deep Neural Networks (DNNs). However, even the most successful methods are still rather failing when adaptation to specific…

Audio and Speech Processing · Electrical Eng. & Systems 2021-04-16 Clément Le Moine , Nicolas Obin , Axel Roebel

We describe a neural network-based system for text-to-speech (TTS) synthesis that is able to generate speech audio in the voice of many different speakers, including those unseen during training. Our system consists of three independently…

Computation and Language · Computer Science 2019-01-04 Ye Jia , Yu Zhang , Ron J. Weiss , Quan Wang , Jonathan Shen , Fei Ren , Zhifeng Chen , Patrick Nguyen , Ruoming Pang , Ignacio Lopez Moreno , Yonghui Wu

In this work we explored building automatic speech recognition models for transcribing doctor patient conversation. We collected a large scale dataset of clinical conversations ($14,000$ hr), designed the task to represent the real word…

This work presents a novel framework based on feed-forward neural network for text-independent speaker classification and verification, two related systems of speaker recognition. With optimized features and model training, it achieves 100%…

Sound · Computer Science 2017-03-20 Zhenhao Ge , Ananth N. Iyer , Srinath Cheluvaraja , Ram Sundaram , Aravind Ganapathiraju

Continuous speech separation plays a vital role in complicated speech related tasks such as conversation transcription. The separation model extracts a single speaker signal from a mixed speech. In this paper, we use transformer and…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-23 Sanyuan Chen , Yu Wu , Zhuo Chen , Jian Wu , Jinyu Li , Takuya Yoshioka , Chengyi Wang , Shujie Liu , Ming Zhou

Most neural network speech enhancement models ignore speech production mathematical models by directly mapping Fourier transform spectrums or waveforms. In this work, we propose a neural source filter network for speech enhancement.…

Sound · Computer Science 2022-10-31 Shulin He , Wei Rao , Jinjiang Liu , Jun Chen , Yukai Ju , Xueliang Zhang , Yannan Wang , Shidong Shang

Character-based neural models have recently proven very useful for many NLP tasks. However, there is a gap of sophistication between methods for learning representations of sentences and words. While most character models for learning…

Computation and Language · Computer Science 2018-10-31 Yingwei Xin , Ethan Hart , Vibhuti Mahajan , Jean-David Ruvini

Recently, end-to-end speech recognition with a hybrid model consisting of the connectionist temporal classification(CTC) and the attention encoder-decoder achieved state-of-the-art results. In this paper, we propose a novel CTC decoder…

Sound · Computer Science 2018-11-02 Zhe Yuan , Zhuoran Lyu , Jiwei Li , Xi Zhou

Most state-of-the-art Deep Learning (DL) approaches for speaker recognition work on a short utterance level. Given the speech signal, these algorithms extract a sequence of speaker embeddings from short segments and those are averaged to…

Sound · Computer Science 2019-07-03 Miquel India , Pooyan Safari , Javier Hernando

We propose a neural sequence-to-sequence model for direction following, a task that is essential to realizing effective autonomous agents. Our alignment-based encoder-decoder model with long short-term memory recurrent neural networks…

Computation and Language · Computer Science 2015-12-18 Hongyuan Mei , Mohit Bansal , Matthew R. Walter

Compensation for channel mismatch and noise interference is essential for robust automatic speech recognition. Enhanced speech has been introduced into the multi-condition training of acoustic models to improve their generalization ability.…

Sound · Computer Science 2022-11-24 Hung-Shin Lee , Pin-Yuan Chen , Yao-Fei Cheng , Yu Tsao , Hsin-Min Wang

Advanced neural network models have penetrated Automatic Speech Recognition (ASR) in recent years, however, in language modeling many systems still rely on traditional Back-off N-gram Language Models (BNLM) partly or entirely. The reason…

Audio and Speech Processing · Electrical Eng. & Systems 2020-09-04 Balázs Tarján , György Szaszák , Tibor Fegyó , Péter Mihajlik

General accent recognition (AR) models tend to directly extract low-level information from spectrums, which always significantly overfit on speakers or channels. Considering accent can be regarded as a series of shifts relative to native…

Sound · Computer Science 2022-07-04 Qijie Shao , Jinghao Yan , Jian Kang , Pengcheng Guo , Xian Shi , Pengfei Hu , Lei Xie

We consider the design of two-pass voice trigger detection systems. We focus on the networks in the second pass that are used to re-score candidate segments obtained from the first-pass. Our baseline is an acoustic model(AM), with BiLSTM…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-07 Saurabh Adya , Vineet Garg , Siddharth Sigtia , Pramod Simha , Chandra Dhir

Streaming end-to-end automatic speech recognition (ASR) models are widely used on smart speakers and on-device applications. Since these models are expected to transcribe speech with minimal latency, they are constrained to be causal with…