English
Related papers

Related papers: Device-directed Utterance Detection

200 papers

We present Deep Speaker, a neural speaker embedding system that maps utterances to a hypersphere where speaker similarity is measured by cosine similarity. The embeddings generated by Deep Speaker can be used for many tasks, including…

Computation and Language · Computer Science 2017-05-08 Chao Li , Xiaokong Ma , Bing Jiang , Xiangang Li , Xuewei Zhang , Xiao Liu , Ying Cao , Ajay Kannan , Zhenyao Zhu

While standard speaker diarization attempts to answer the question "who spoken when", most of relevant applications in reality are more interested in determining "who spoken what". Whether it is the conventional modularized approach or the…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-18 Yiling Huang , Weiran Wang , Guanlong Zhao , Hank Liao , Wei Xia , Quan Wang

In this paper, we have investigated recurrent deep neural networks (DNNs) in combination with regularization techniques as dropout, zoneout, and regularization post-layer. As a benchmark, we chose the TIMIT phone recognition task due to its…

Computation and Language · Computer Science 2018-06-20 Jan Vanek , Josef Michalek , Josef Psutka

Confidence scores are very useful for downstream applications of automatic speech recognition (ASR) systems. Recent works have proposed using neural networks to learn word or utterance confidence scores for end-to-end ASR. In those studies,…

Audio and Speech Processing · Electrical Eng. & Systems 2021-04-28 David Qiu , Yanzhang He , Qiujia Li , Yu Zhang , Liangliang Cao , Ian McGraw

Attention-based recurrent neural encoder-decoder models present an elegant solution to the automatic speech recognition problem. This approach folds the acoustic model, pronunciation model, and language model into a single network and…

Audio and Speech Processing · Electrical Eng. & Systems 2018-11-08 Shubham Toshniwal , Anjuli Kannan , Chung-Cheng Chiu , Yonghui Wu , Tara N Sainath , Karen Livescu

This paper summarizes our submission to Task 2 of the second track of the 10th Dialog System Technology Challenge (DSTC10) "Knowledge-grounded Task-oriented Dialogue Modeling on Spoken Conversations". Similar to the previous year's…

Computation and Language · Computer Science 2021-12-17 David Thulke , Nico Daheim , Christian Dugast , Hermann Ney

While machine learning techniques are traditionally resource intensive, we are currently witnessing an increased interest in hardware and energy efficient approaches. This need for resource-efficient machine learning is primarily driven by…

Audio and Speech Processing · Electrical Eng. & Systems 2020-07-23 Lukas Pfeifenberger , Matthias Zöhrer , Günther Schindler , Wolfgang Roth , Holger Fröning , Franz Pernkopf

Deep neural networks have become an indispensable technique for audio source separation (ASS). It was recently reported that a variant of CNN architecture called MMDenseNet was successfully employed to solve the ASS problem of estimating…

Sound · Computer Science 2018-05-30 Naoya Takahashi , Nabarun Goswami , Yuki Mitsufuji

End-to-end approaches for automatic speech recognition (ASR) benefit from directly modeling the probability of the word sequence given the input audio stream in a single neural network. However, compared to conventional ASR systems, these…

Audio and Speech Processing · Electrical Eng. & Systems 2020-02-19 Ankur Gandhe , Ariya Rastrow

We introduce a novel method for controlling the functionality of a hands-free speech communication device which comprises a model-based acoustic echo canceller (AEC), minimum variance distortionless response (MVDR) beamformer (BF) and…

Audio and Speech Processing · Electrical Eng. & Systems 2022-08-11 Thomas Haubner , Walter Kellermann

This paper presents a framework for converting wireless signals into structured datasets, which can be fed into machine learning algorithms for the detection of active eavesdropping attacks at the physical layer. More specifically, a…

Signal Processing · Electrical Eng. & Systems 2021-02-24 Tiep M. Hoang , Trung Q. Duong , Hoang Duong Tuan , Sangarapillai Lambotharan , Emi Garcia-Palacios , Long D. Nguyen

This paper introduces a lightweight deep learning model for real-time speech enhancement, designed to operate efficiently on resource-constrained devices. The proposed model leverages a compact architecture that facilitates rapid inference…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-23 Shuubham Ojha , Felix Gervits , Carol Espy-Wilson

Despite the tremendous success of automatic speech recognition (ASR) with the introduction of deep learning, its performance is still unsatisfactory in many real-world multi-talker scenarios. Speaker separation excels in separating…

Sound · Computer Science 2025-03-25 Yufeng Yang , Hassan Taherian , Vahid Ahmadi Kalkhorani , DeLiang Wang

Dual learning is a paradigm for semi-supervised machine learning that seeks to leverage unsupervised data by solving two opposite tasks at once. In this scheme, each model is used to generate pseudo-labels for unlabeled examples that are…

Computation and Language · Computer Science 2023-01-12 Cal Peyser , Ronny Huang , Tara Sainath , Rohit Prabhavalkar , Michael Picheny , Kyunghyun Cho

Automatic speech recognition (ASR) models are typically designed to operate on a single input data type, e.g. a single or multi-channel audio streamed from a device. This design decision assumes the primary input data source does not change…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-30 Gokce Keskin , Minhua Wu , Brian King , Harish Mallidi , Yang Gao , Jasha Droppo , Ariya Rastrow , Roland Maas

Recent studies on pronunciation scoring have explored the effect of introducing phone embeddings as reference pronunciation, but mostly in an implicit manner, i.e., addition or concatenation of reference phone embedding and actual…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-14 Wei Liu , Kaiqi Fu , Xiaohai Tian , Shuju Shi , Wei Li , Zejun Ma , Tan Lee

We introduce a new beam search decoder that is fully differentiable, making it possible to optimize at training time through the inference procedure. Our decoder allows us to combine models which operate at different granularities (e.g.…

Computation and Language · Computer Science 2019-02-19 Ronan Collobert , Awni Hannun , Gabriel Synnaeve

This paper addresses the combination of complementary parallel speech recognition systems to reduce the error rate of speech recognition systems operating in real highly-reverberant environments. First, the testing environment consists of…

Audio and Speech Processing · Electrical Eng. & Systems 2019-06-19 José Novoa , Josué Fredes , Jorge Wuth , Fernando Huenupán , Richard M. Stern , Nestor Becerra Yoma

Children speech recognition is indispensable but challenging due to the diversity of children's speech. In this paper, we propose a filter-based discriminative autoencoder for acoustic modeling. To filter out the influence of various…

Computation and Language · Computer Science 2022-05-24 Chiang-Lin Tai , Hung-Shin Lee , Yu Tsao , Hsin-Min Wang

Recurrent neural networks (RNNs) are a powerful model for sequential data. End-to-end training methods such as Connectionist Temporal Classification make it possible to train RNNs for sequence labelling problems where the input-output…

Neural and Evolutionary Computing · Computer Science 2013-03-26 Alex Graves , Abdel-rahman Mohamed , Geoffrey Hinton