中文
相关论文

相关论文: "Sorry, I Didn't Catch That": How Speech Models Mi…

200 篇论文

We address quality assessment for neural network based ASR by providing explanations that help increase our understanding of the system and ultimately help build trust in the system. Compared to simple classification labels, explaining…

声音 · 计算机科学 2023-03-01 Xiaoliang Wu , Peter Bell , Ajitha Rajan

This paper explores the pitfalls in evaluating multilingual automatic speech recognition (ASR) models, with a particular focus on Indic language scripts. We investigate the text normalization routine employed by leading ASR models,…

计算与语言 · 计算机科学 2024-11-12 Kavya Manohar , Leena G Pillai , Elizabeth Sherly

When evaluating the performance of automatic speech recognition models, usually word error rate within a certain dataset is used. Special care must be taken in understanding the dataset in order to report realistic performance numbers. We…

计算与语言 · 计算机科学 2021-05-21 Aashish Agarwal , Torsten Zesch

Recent work in automatic recognition of conversational telephone speech (CTS) has achieved accuracy levels comparable to human transcribers, although there is some debate how to precisely quantify human performance on this task, using the…

计算与语言 · 计算机科学 2022-02-22 Andreas Stolcke , Jasha Droppo

Large language models have been proven quite beneficial for a variety of automatic speech recognition tasks in Google. We summarize results on Voice Search and a few YouTube speech transcription tasks to highlight the impact that one can…

计算与语言 · 计算机科学 2012-11-01 Ciprian Chelba , Dan Bikel , Maria Shugrina , Patrick Nguyen , Shankar Kumar

The conventional paradigm in speech translation starts with a speech recognition step to generate transcripts, followed by a translation step with the automatic transcripts as input. To address various shortcomings of this paradigm, recent…

计算与语言 · 计算机科学 2020-08-31 Matthias Sperber , Hendra Setiawan , Christian Gollan , Udhyakumar Nallasamy , Matthias Paulik

The performance of Automatic Speech Recognition (ASR) systems has constantly increased in state-of-the-art development. However, performance tends to decrease considerably in more challenging conditions (e.g., background noise, multiple…

计算与语言 · 计算机科学 2024-05-24 Ronald Cumbal , Birger Moell , Jose Lopes , Olof Engwall

The recently proposed Sequence-to-Sequence (seq2seq) framework advocates replacing complex data processing pipelines, such as an entire automatic speech recognition system, with a single neural network trained in an end-to-end fashion. In…

神经与进化计算 · 计算机科学 2016-12-09 Jan Chorowski , Navdeep Jaitly

Most spoken language translation systems developed to date rely on a pipelined architecture, in which the main stages are speech recognition, linguistic analysis, transfer, generation and speech synthesis. When making projections of error…

cmp-lg · 计算机科学 2008-02-03 Manny Rayner , David Carter , Patti Price , Bertil Lyberg

Speech recognizers trained on close-talking speech do not generalize to distant speech and the word error rate degradation can be as large as 40% absolute. Most studies focus on tackling distant speech recognition as a separate problem,…

计算与语言 · 计算机科学 2018-06-14 Hao Tang , Wei-Ning Hsu , Francois Grondin , James Glass

Automatic speech recognition (ASR) systems are designed to transcribe spoken language into written text and find utility in a variety of applications including voice assistants and transcription services. However, it has been observed that…

计算与语言 · 计算机科学 2023-07-21 Anand Kumar Rai , Siddharth D Jaiswal , Animesh Mukherjee

State-of-the-art automatic speech recognition (ASR) models like Whisper, perform poorly on atypical speech, such as that produced by individuals with dysarthria. Past works for atypical speech have mostly investigated fully personalized (or…

声音 · 计算机科学 2025-09-23 Vishnu Raja , Adithya V Ganesan , Anand Syamkumar , Ritwik Banerjee , H Andrew Schwartz

Speech recognition is very challenging in student learning environments that are characterized by significant cross-talk and background noise. To address this problem, we present a bilingual speech recognition system that uses an…

Recent progress in generative AI has made it increasingly easy to create natural-sounding deepfake speech from just a few seconds of audio. While these tools support helpful applications, they also raise serious concerns by making it…

音频与语音处理 · 电气工程与系统科学 2025-08-07 Xi Xuan , Yang Xiao , Rohan Kumar Das , Tomi Kinnunen

Speaker attribution from speech transcripts is the task of identifying a speaker from the transcript of their speech based on patterns in their language use. This task is especially useful when the audio is unavailable (e.g. deleted) or…

计算与语言 · 计算机科学 2026-01-27 Cristina Aggazzotti , Matthew Wiesner , Elizabeth Allyn Smith , Nicholas Andrews

Dysarthria is a speech disorder that hinders communication due to difficulties in articulating words. Detection of dysarthria is important for several reasons as it can be used to develop a treatment plan and help improve a person's quality…

Large-scale, weakly-supervised speech recognition models, such as Whisper, have demonstrated impressive results on speech recognition across domains and languages. However, their application to long audio transcription via buffered or…

声音 · 计算机科学 2023-07-12 Max Bain , Jaesung Huh , Tengda Han , Andrew Zisserman

The problem of synthetic speech detection has enjoyed considerable attention, with recent methods achieving low error rates across several established benchmarks. However, to what extent can low error rates on academic benchmarks translate…

音频与语音处理 · 电气工程与系统科学 2025-05-23 Ashi Garg , Zexin Cai , Lin Zhang , Henry Li Xinyuan , Leibny Paola García-Perera , Kevin Duh , Sanjeev Khudanpur , Matthew Wiesner , Nicholas Andrews

Speaker diarization systems segment a conversation recording based on the speakers' identity. Such systems can misclassify the speaker of a portion of audio due to a variety of factors, such as speech pattern variation, background noise,…

声音 · 计算机科学 2024-06-26 Anurag Chowdhury , Abhinav Misra , Mark C. Fuhs , Monika Woszczyna

Transcribing voice communications in NASA's launch control center is important for information utilization. However, automatic speech recognition in this environment is particularly challenging due to the lack of training data, unfamiliar…

计算与语言 · 计算机科学 2018-04-26 Kyongsik Yun , Joseph Osborne , Madison Lee , Thomas Lu , Edward Chow