Google usm: Scaling automatic speech recognition beyond 100 languages
We introduce the Universal Speech Model (USM), a single large model that performs
automatic speech recognition (ASR) across 100+ languages. This is achieved by pre …
automatic speech recognition (ASR) across 100+ languages. This is achieved by pre …
[图书][B] Markov models for pattern recognition: from theory to applications
GA Fink - 2014 - books.google.com
Markov models are extremely useful as a general, widely applicable tool for many areas in
statistical pattern recognition. This unique text/reference places the formalism of Markov …
statistical pattern recognition. This unique text/reference places the formalism of Markov …
Speaking in shorthand–A syllable-centric perspective for understanding pronunciation variation
S Greenberg - Speech Communication, 1999 - Elsevier
Current-generation automatic speech recognition (ASR) systems model spoken discourse
as a quasi-linear sequence of words and phones. Because it is unusual for every phone …
as a quasi-linear sequence of words and phones. Because it is unusual for every phone …
[PDF][PDF] The use of context in large vocabulary speech recognition
JJ Odell - 1995 - Citeseer
In recent years, considerable progress has been made in the eld of continuous speech
recognition where the predominant technology is based on hidden Markov models (HMMs) …
recognition where the predominant technology is based on hidden Markov models (HMMs) …
Menu-driven voice control of characters in a game environment
SCH Luisi - US Patent 7,233,904, 2007 - Google Patents
In a gaming system, a user controls actions of characters in the game environment using
speech commands. In a learn ing mode, available speech commands are displayed in a …
speech commands. In a learn ing mode, available speech commands are displayed in a …
A word graph algorithm for large vocabulary continuous speech recognition
S Ortmanns, H Ney, X Aubert - Computer Speech & Language, 1997 - Elsevier
This paper describes a method for the construction of a word graph (or lattice) for large
vocabulary, continuous speech recognition. The advantage of a word graph is that a fairly …
vocabulary, continuous speech recognition. The advantage of a word graph is that a fairly …
Dynamic programming search for continuous speech recognition
H Ney, S Ortmanns - IEEE Signal Processing Magazine, 1999 - ieeexplore.ieee.org
The authors gives a unifying view of the dynamic programming approach to the search
problem. They review the search problem from the statistical point-of-view and show how the …
problem. They review the search problem from the statistical point-of-view and show how the …
[PDF][PDF] 1993 benchmark tests for the ARPA spoken language program
DS Pallett, JG Fiscus, WM Fisher… - … : Proceedings of a …, 1994 - aclanthology.org
This paper reports results obtained in benchmark tests conducted within the ARPA Spoken
Language program in November and December of 1993. In addition to ARPA contractors …
Language program in November and December of 1993. In addition to ARPA contractors …
Neural networks for statistical recognition of continuous speech
N Morgan, HA Bourlard - Proceedings of the IEEE, 1995 - ieeexplore.ieee.org
In recent years there has been a significant body of work, both theoretical and experimental,
that has established the viability of artificial neural networks (ANN's) as a useful technology …
that has established the viability of artificial neural networks (ANN's) as a useful technology …
Progress in dynamic programming search for LVCSR
H Ney, S Ortmanns - Proceedings of the IEEE, 2000 - ieeexplore.ieee.org
Initially introduced in the late 1960s and early 1970s, dynamic programming algorithms
have become increasingly popular in automatic speech recognition. There are two reasons …
have become increasingly popular in automatic speech recognition. There are two reasons …