English
Related papers

Related papers: Towards Real-time Mispronunciation Detection in Ki…

200 papers

Recently, end-to-end mispronunciation detection and diagnosis (MD&D) systems has become a popular alternative to greatly simplify the model-building process of conventional hybrid DNN-HMM systems by representing complicated modules with a…

Computation and Language · Computer Science 2021-04-20 Kaiqi Fu , Jones Lin , Dengfeng Ke , Yanlu Xie , Jinsong Zhang , Binghuai Lin

A sequence-to-sequence learning with neural networks has empirically proven to be an effective framework for Chinese Spelling Correction (CSC), which takes a sentence with some spelling errors as input and outputs the corrected one.…

Computation and Language · Computer Science 2021-06-02 Chong Li , Cenyuan Zhang , Xiaoqing Zheng , Xuanjing Huang

We present results that show it is possible to build a competitive, greatly simplified, large vocabulary continuous speech recognition system with whole words as acoustic units. We model the output vocabulary of about 100,000 words directly…

Computation and Language · Computer Science 2016-11-01 Hagen Soltau , Hank Liao , Hasim Sak

In large-scale domain classification, an utterance can be handled by multiple domains with overlapped capabilities. However, only a limited number of ground-truth domains are provided for each training utterance in practice while knowing as…

Computation and Language · Computer Science 2020-03-10 Joo-Kyung Kim , Young-Bum Kim

State-of-the-art natural language understanding classification models follow two-stages: pre-training a large language model on an auxiliary task, and then fine-tuning the model on a task-specific labeled dataset using cross-entropy loss.…

Computation and Language · Computer Science 2021-04-06 Beliz Gunel , Jingfei Du , Alexis Conneau , Ves Stoyanov

In-context learning enables language models (LM) to adapt to downstream data or tasks by incorporating few samples as demonstrations within the prompts. It offers strong performance without the expense of fine-tuning. However, the…

Computation and Language · Computer Science 2024-10-15 Jian Gu , Aldeida Aleti , Chunyang Chen , Hongyu Zhang

Online speech recognition is crucial for developing natural human-machine interfaces. This modality, however, is significantly more challenging than off-line ASR, since real-time/low-latency constraints inevitably hinder the use of future…

Audio and Speech Processing · Electrical Eng. & Systems 2018-06-13 Mirco Ravanelli , Dmitriy Serdyuk , Yoshua Bengio

Acoustic-to-articulatory speech inversion could enhance automated clinical mispronunciation detection to provide detailed articulatory feedback unattainable by formant-based mispronunciation detection algorithms; however, it is unclear the…

Audio and Speech Processing · Electrical Eng. & Systems 2023-08-22 Nina R Benway , Yashish M Siriwardena , Jonathan L Preston , Elaine Hitchcock , Tara McAllister , Carol Espy-Wilson

Existing multilingual embedding models often encounter challenges in cross-lingual scenarios due to imbalanced linguistic resources and less consideration of cross-lingual alignment during training. Although standardized contrastive…

Computation and Language · Computer Science 2026-04-15 Seungyoon Lee , Minhyuk Kim , Seongtae Hong , Youngjoon Jang , Dongsuk Oh , Heuiseok Lim

The study of speech disorders can benefit greatly from time-aligned data. However, audio-text mismatches in disfluent speech cause rapid performance degradation for modern speech aligners, hindering the use of automatic approaches. In this…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-05 Theodoros Kouzelis , Georgios Paraskevopoulos , Athanasios Katsamanis , Vassilis Katsouros

Currently, large language models (LLMs) predominantly focus on the text modality. To enable more natural human-AI interaction, speech LLMs are emerging, but building effective end-to-end speech LLMs remains challenging due to limited data…

Computation and Language · Computer Science 2026-04-14 Yan Zhou , Qingkai Fang , Yun Hong , Yang Feng

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

Recently, there has been an increasing interest in end-to-end speech recognition that directly transcribes speech to text without any predefined alignments. One approach is the attention-based encoder-decoder framework that learns a mapping…

Computation and Language · Computer Science 2017-02-02 Suyoun Kim , Takaaki Hori , Shinji Watanabe

Most spoken language understanding systems use a pipeline approach composed of an automatic speech recognition interface and a natural language understanding module. This approach forces hard decisions when converting continuous inputs into…

Computation and Language · Computer Science 2023-10-18 Quentin Meeus , Marie-Francine Moens , Hugo Van hamme

Non-autoregressive translation (NAT) models are typically trained with the cross-entropy loss, which forces the model outputs to be aligned verbatim with the target sentence and will highly penalize small shifts in word positions. Latent…

Computation and Language · Computer Science 2022-10-11 Chenze Shao , Yang Feng

The recent developments in technology have re-warded us with amazing audio synthesis models like TACOTRON and WAVENETS. On the other side, it poses greater threats such as speech clones and deep fakes, that may go undetected. To tackle…

Machine Learning · Computer Science 2021-07-27 Arun Kumar Singh , Priyanka Singh , Karan Nathwani

The performance of deep neural networks improves with more annotated data. The problem is that the budget for annotation is limited. One solution to this is active learning, where a model asks human to annotate data that it perceived as…

Computer Vision and Pattern Recognition · Computer Science 2019-05-10 Donggeun Yoo , In So Kweon

Connectionist temporal classification (CTC) provides an end-to-end acoustic model (AM) training strategy. CTC learns accurate AMs without time-aligned phonetic transcription, but sometimes fails to converge, especially in…

Audio and Speech Processing · Electrical Eng. & Systems 2019-02-28 Di He , Xuesong Yang , Boon Pang Lim , Yi Liang , Mark Hasegawa-Johnson , Deming Chen

This paper introduces a practical approach for leveraging a real-time deep learning model to alternate between speech enhancement and joint speech enhancement and separation depending on whether the input mixture contains one or two active…

Audio and Speech Processing · Electrical Eng. & Systems 2023-10-17 Kashyap Patel , Anton Kovalyov , Issa Panahi

Text recognition methods are gaining rapid development. Some advanced techniques, e.g., powerful modules, language models, and un- and semi-supervised learning schemes, consecutively push the performance on public benchmarks forward.…

Computer Vision and Pattern Recognition · Computer Science 2024-01-01 Ziyin Zhang , Ning Lu , Minghui Liao , Yongshuai Huang , Cheng Li , Min Wang , Wei Peng