IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01.

Công bố khoa học tiêu biểu

* Dữ liệu chỉ mang tính chất tham khảo

Sắp xếp:  
Evaluating speech recognition in the context of a spoken dialogue system: critical error rate
IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01. - - Trang 280-283
G. Damnati
Evaluating a speech recognition system is a key issue towards understanding its deficiencies and focusing potential improvements on useful aspects. When a system is designed for a given application, it is particularly relevant to have an evaluation procedure that reflects the role of the system in this application. Evaluating continuous speech recognition through word error rate is not completely ...... hiện toàn bộ
#Speech recognition #Error analysis #Natural languages #History #Speech processing #Research and development #Delta modulation #Speech analysis #Computer errors #Man machine systems
Author index
IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01. - - Trang 467-468 - 2001
The author index contains an entry for each author and coauthor included in the proceedings record.
Task-specific adaptation of speech recognition models
IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01. - - Trang 433-436
A. Sankar, A. Kannan, B. Shahshahani, E. Jackson
Most published adaptation research focuses on speaker adaptation, and on adaptation for noisy channels and background environments. We study acoustic, grammar, and combined acoustic and grammar adaptation for creating task-specific recognition models. Comprehensive experimental results are presented using data from natural language quotes and a trading application. The results show that task adapt...... hiện toàn bộ
#Speech recognition #Hidden Markov models #Distributed computing #Loudspeakers #Acoustic applications #Adaptation model #Smoothing methods #Acoustic noise #Background noise #Working environment noise
Automatic evaluation methods of a speech translation system's capability
IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01. - - Trang 359-362
F. Sugaya, K. Yasuda, T. Takezawa, S. Yamamoto
The main goal of the paper is to propose automatic schemes for the translation paired comparison method, which was proposed by the authors to evaluate precisely a speech translation system's capability. In the method, the outputs of the speech translation system are subjectively compared with the results of native Japanese taking the Test of English for International Communication (TOEIC), which i...... hiện toàn bộ
#Speech analysis #Natural languages #System testing #Regression analysis #Humans #Laboratories #Performance evaluation #Costs #Text recognition
Evaluating long-term spectral subtraction for reverberant ASR
IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01. - - Trang 103-106
D. Gelbart, N. Morgan
Even a modest degree of room reverberation can greatly increase the difficulty of automatic speech recognition. We have observed large increases in speech recognition word error rates when using a far-field (3-6 feet) microphone in a conference room, in comparison with recordings from head-mounted microphones. In this paper, we describe experiments with a proposed remedy based on the subtraction o...... hiện toàn bộ
#Automatic speech recognition #Spectral analysis #Reverberation #Speech recognition #Microwave integrated circuits #Cepstral analysis #Computer science #Error analysis #Absorption #Fourier transforms
Dialogue management in the Talk'n'Travel system
IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01. - - Trang 235-239
D. Stallard
A central problem for mixed-initiative dialogue management is coping with user utterances that fall outside of the expected sequence of dialogue. Independent initiative by the user may require a complete revision of the future course of the dialogue, even when the system is engaged in activities of its own, such as querying a database, etc. This paper presents an event-driven, goal-based dialogue ...... hiện toàn bộ
#Databases #Natural languages #Technology management #Prototypes #Telephony #Speech recognition #Robustness #Communication system control
Beyond the Informedia digital video library: video and audio analysis for remembering conversations
IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01. - - Trang 296-300
A.G. Hauptmann, Wei-Hao Lin
The Informedia Project digital video library pioneered the automatic analysis of television broadcast news and its retrieval on demand. Building on that system, we have developed a wearable, personalized Informedia system, which listens to and transcribes the wearer's part of a conversation, recognizes the face of the current dialog partner and remembers his/her voice. The next time the system see...... hiện toàn bộ
#Software libraries #Digital video broadcasting #Digital audio broadcasting #Face recognition #Speech recognition #Space technology #Global Positioning System #Computer science #TV broadcasting #Automatic speech recognition
Estimated rank pruning and Java-based speech recognition
IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01. - - Trang 401-404
N. Jevtic, A. Klautau, A. Orlitsky
Most speech recognition systems search through large finite state machines to find the most likely path, or hypothesis. Efficient search in these large spaces requires pruning of some hypotheses. Popular pruning techniques include probability pruning which keeps only hypotheses whose probability falls within a prescribed factor from the most likely one, and rank pruning which keeps only a prescrib...... hiện toàn bộ
#Java #Speech recognition #Sorting #Decoding #Histograms #Size control #System testing #Graphical user interfaces #Parameter estimation
Distributed speech recognition with codec parameters
IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01. - - Trang 127-130
B. Raj, J. Migdal, R. Singh
Communication devices which perform distributed speech recognition (DSR) tasks currently transmit standardized coded parameters of speech signals. Recognition features are extracted from signals reconstructed using these on a remote server. Since reconstruction losses degrade recognition performance, proposals are being considered to standardize DSR-codecs which derive recognition features, to be ...... hiện toàn bộ
#Speech recognition #Codecs #Feature extraction #GSM #Propagation losses #Degradation #Performance loss #Proposals #Code standards #Linear predictive coding
Automatic selection of transcribed training material
IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01. - - Trang 417-420
T.M. Kamm, G.G.L. Meyer
Conventional wisdom says that incorporating more training data is the surest way to reduce the error rate of a speech recognition system. This, in turn, guarantees that speech recognition systems are expensive to train, because of the high cost of annotating training data. We propose an iterative training algorithm that seeks to improve the error rate of a speech recognizer without incurring addit...... hiện toàn bộ
#Speech recognition #Error analysis #Iterative algorithms #Training data #Costs #System testing #Natural languages #Speech processing #Data mining #Automatic speech recognition
Tổng số: 112   
  • 1
  • 2
  • 3
  • 4
  • 5
  • 6
  • 10