English
Related papers

Related papers: Voice trigger detection from LVCSR hypothesis latt…

200 papers

Recurrent neural network (RNN) language models (LMs) and Long Short Term Memory (LSTM) LMs, a variant of RNN LMs, have been shown to outperform traditional N-gram LMs on speech recognition tasks. However, these models are computationally…

Machine Learning · Statistics 2017-11-16 Shankar Kumar , Michael Nirschl , Daniel Holtmann-Rice , Hank Liao , Ananda Theertha Suresh , Felix Yu

Interactions with virtual assistants typically start with a predefined trigger phrase followed by the user command. To make interactions with the assistant more intuitive, we explore whether it is feasible to drop the requirement that users…

Computation and Language · Computer Science 2024-03-27 Dominik Wagner , Alexander Churchill , Siddharth Sigtia , Panayiotis Georgiou , Matt Mirsamadi , Aarshee Mishra , Erik Marchi

Modern mispronunciation detection and diagnosis systems have seen significant gains in accuracy due to the introduction of deep learning. However, these systems have not been evaluated for the ability to be run in real-time, an important…

Audio and Speech Processing · Electrical Eng. & Systems 2020-03-05 Peter Plantinga , Eric Fosler-Lussier

Streaming Automatic Speech Recognition (ASR) in voice assistants can utilize prefetching to partially hide the latency of response generation. Prefetching involves passing a preliminary ASR hypothesis to downstream systems in order to…

Computation and Language · Computer Science 2023-05-24 Andreas Schwarz , Di He , Maarten Van Segbroeck , Mohammed Hethnawi , Ariya Rastrow

For end-to-end Automatic Speech Recognition (ASR) models, recognizing personal or rare phrases can be hard. A promising way to improve accuracy is through spelling correction (or rewriting) of the ASR lattice, where potentially…

Computation and Language · Computer Science 2024-09-26 Leonid Velikovich , Christopher Li , Diamantino Caseiro , Shankar Kumar , Pat Rondon , Kandarp Joshi , Xavier Velez

Deep LSTM is an ideal candidate for text recognition. However text recognition involves some initial image processing steps like segmentation of lines and words which can induce error to the recognition system. Without segmentation,…

Computer Vision and Pattern Recognition · Computer Science 2015-02-27 Anupama Ray , Sai Rajeswar , Santanu Chaudhury

The prevailing noise-resistant and reverberation-resistant localization algorithms primarily emphasize separating and providing directional output for each speaker in multi-speaker scenarios, without association with the identity of…

Sound · Computer Science 2023-10-18 Yu Chen , Xinyuan Qian , Zexu Pan , Kainan Chen , Haizhou Li

While the community keeps promoting end-to-end models over conventional hybrid models, which usually are long short-term memory (LSTM) models trained with a cross entropy criterion followed by a sequence discriminative training criterion,…

Audio and Speech Processing · Electrical Eng. & Systems 2020-03-18 Jinyu Li , Rui Zhao , Eric Sun , Jeremy H. M. Wong , Amit Das , Zhong Meng , Yifan Gong

We address the problem of detecting speech directed to a device that does not contain a specific wake-word. Specifically, we focus on audio coming from a touch-based invocation. Mitigating virtual assistants (VAs) activation due to…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-31 Vineet Garg , Ognjen Rudovic , Pranay Dighe , Ahmed H. Abdelaziz , Erik Marchi , Saurabh Adya , Chandra Dhir , Ahmed Tewfik

The input to a neural sequence-to-sequence model is often determined by an up-stream system, e.g. a word segmenter, part of speech tagger, or speech recognizer. These up-stream models are potentially error-prone. Representing inputs through…

Computation and Language · Computer Science 2017-07-24 Matthias Sperber , Graham Neubig , Jan Niehues , Alex Waibel

Despite recent advances in end-to-end speech recognition methods, the output tends to be biased to the training data's vocabulary, resulting in inaccurate recognition of proper nouns and other unknown terms. To address this issue, we…

Computation and Language · Computer Science 2025-06-03 Yu Nakagome , Michael Hentschel

Identifying mistakes (i.e., miscues) made while reading aloud is commonly approached post-hoc by comparing automatic speech recognition (ASR) transcriptions to the target reading text. However, post-hoc methods perform poorly when ASR…

Machine Learning · Computer Science 2025-05-30 Griffin Dietz Smith , Dianna Yee , Jennifer King Chen , Leah Findlater

Long short-term memory (LSTM) based acoustic modeling methods have recently been shown to give state-of-the-art performance on some speech recognition tasks. To achieve a further performance improvement, in this research, deep extensions on…

Computation and Language · Computer Science 2015-05-12 Xiangang Li , Xihong Wu

In this paper, we address the task of determining whether a given utterance is directed towards a voice-enabled smart-assistant device or not. An undirected utterance is termed as a "false trigger" and false trigger mitigation (FTM) is…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-22 Pranay Dighe , Erik Marchi , Srikanth Vishnubhotla , Sachin Kajarekar , Devang Naik

Recently, there has been growth in providers of speech transcription services enabling others to leverage technology they would not normally be able to use. As a result, speech-enabled solutions have become commonplace. Their success…

Audio and Speech Processing · Electrical Eng. & Systems 2020-03-17 Alexandros Kastanos , Anton Ragni , Mark Gales

End-to-end (E2E) models have made rapid progress in automatic speech recognition (ASR) and perform competitively relative to conventional models. To further improve the quality, a two-pass model has been proposed to rescore streamed…

Audio and Speech Processing · Electrical Eng. & Systems 2020-03-19 Ke Hu , Tara N. Sainath , Ruoming Pang , Rohit Prabhavalkar

The success of automatic speaker verification shows that discriminative speaker representations can be extracted from neutral speech. However, as a kind of non-verbal voice, laughter should also carry speaker information intuitively. Thus,…

Audio and Speech Processing · Electrical Eng. & Systems 2023-11-21 Yuke Lin , Xiaoyi Qin , Huahua Cui , Zhenyi Zhu , Ming Li

Voice triggering (VT) enables users to activate their devices by just speaking a trigger phrase. A front-end system is typically used to perform speech enhancement and/or separation, and produces multiple enhanced and/or separated signals.…

Audio and Speech Processing · Electrical Eng. & Systems 2024-02-15 Takuya Higuchi , Avamarie Brueggeman , Masood Delfarah , Stephen Shum

We investigate the effectiveness of using a large ensemble of advanced neural language models (NLMs) for lattice rescoring on automatic speech recognition (ASR) hypotheses. Previous studies have reported the effectiveness of combining a…

Audio and Speech Processing · Electrical Eng. & Systems 2023-12-21 Atsunori Ogawa , Naohiro Tawara , Marc Delcroix , Shoko Araki

In this paper, we propose a speaker-verification system based on maximum likelihood linear regression (MLLR) super-vectors, for which speakers are characterized by m-vectors. These vectors are obtained by a uniform segmentation of the…

Sound · Computer Science 2016-05-13 A. K. Sarkar , C. Barras , V. B. Le , D. Matrouf