Results 41 to 50 of about 3,404,666 (322)
Non-autoregressive Transformer Chinese Speech Recognition Incorporating Pronunciation- Character Representation Conversion [PDF]
Jisuanji kexue, 2023 The Transformer based on self-attention mechanism shows powerful model performance in speech recognition tasks,where the non-autoregressive Transformer automatic speech recognition model has a faster decoding speed compared with the autoregressive model ...
TENG Sihang, WANG Lie, LI Ya
doaj +1 more source
Racial disparities in automated speech recognition
Proceedings of the National Academy of Sciences of the United States of America, 2020 Significance Automated speech recognition (ASR) systems are now used in a variety of applications to convert spoken language to text, from virtual assistants, to closed captioning, to hands-free computing.
Allison Koenecke +9 more
semanticscholar +1 more source
Gazi Üniversitesi Fen Bilimleri Dergisi, 2019 Speech is a paramount means of communication among humans, which makes recognition of the speech by computers is a study area of significance. In this research area, many studies have been carried out based on different languages.
Saadin OYUCU +2 more
doaj +1 more source
EURASIP Journal on Audio, Speech, and Music Processing, 2021 The performance of speech recognition systems trained with neutral utterances degrades significantly when these systems are tested with emotional speech. Since everybody can speak emotionally in the real-world environment, it is necessary to take account
Masoud Geravanchizadeh +2 more
doaj +1 more source
All Politics is Local: The Renminbi's Prospects as a Future Global Currency [PDF]
, 2000 . In this article we describe methods for improving the RWTH German speech recognizer used within the VERBMOBIL project. In particular, we present acceleration methods for the search based on both within-word and across-word phoneme models. We also study
A Sixtus +16 more
core +3 more sources
A novel privacy-preserving speech recognition framework using bidirectional LSTM
Journal of Cloud Computing: Advances, Systems and Applications, 2020 Utilizing speech as the transmission medium in Internet of things (IoTs) is an effective way to reduce latency while improving the efficiency of human-machine interaction. In the field of speech recognition, Recurrent Neural Network (RNN) has significant
Qingren Wang +4 more
doaj +1 more source
Streaming Automatic Speech Recognition with the Transformer Model [PDF]
IEEE International Conference on Acoustics, Speech, and Signal Processing, 2020 Encoder-decoder based sequence-to-sequence models have demonstrated state-of-the-art results in end-to-end automatic speech recognition (ASR). Recently, the transformer architecture, which uses self-attention to model temporal context information, has ...
Niko Moritz +2 more
semanticscholar +1 more source
Streaming End-to-End Target-Speaker Automatic Speech Recognition and Activity Detection
IEEE Access, 2023 Automatic speech recognition of a target speaker in the presence of interfering speakers remains a challenging issue. One approach to tackle this problem is target-speaker speech recognition, which conditions the recognition process on an embedding that ...
Takafumi Moriya +4 more
doaj +1 more source
Selection of acoustic modeling unit for Tibetan speech recognition based on deep learning [PDF]
MATEC Web of Conferences, 2021 The selection of the speech recognition modeling unit is the primary problem of acoustic modeling in speech recognition, and different acoustic modeling units will directly affect the overall performance of speech recognition.
Gong Baojia +4 more
doaj +1 more source
Design and implementation of a user-oriented speech recognition interface: the synergy of technology and human factors [PDF]
, 1994 The design and implementation of a user-oriented speech recognition interface are described. The interface enables the use of speech recognition in so-called interactive voice response systems which can be accessed via a telephone connection.
Kloosterman, Sietse H.
core +4 more sources