IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01.
Cơ quản chủ quản: N/A
Các bài báo tiêu biểu
ETUDE, a recursive dialog manager with embedded user interface patterns
- Trang 244-247
We describe ETUDE, a dialog manager that supports recursive descriptions of the
dialog flow in spoken dialog applications. We also introduce the notion of user
interface patterns, i.e. those dialog patterns that are frequently used in
applications. We then describe how these patterns can be built into the dialog
manager engine in order to facilitate the design and development of complex
applicatio...
#User interfaces #Telephony #Control systems #Costs #Winches #Engines #Logic #Navigation #Usability #Design automation
Comparison of standard and hybrid modeling techniques for distributed speech recognition
- Trang 143-146
Distributed speech recognition (DSR) is an interesting technology for mobile
recognition tasks where the recognizer is split up into two parts and connected
by a transmission channel. We compare the performance of standard and hybrid
modeling approaches in this environment. The evaluation is done on clean and
noisy speech samples taken from the TI digits and the Aurora databases. Our
results show ...
#Speech recognition #Hidden Markov models #Bit rate #Vector quantization #Bandwidth #Channel coding #Computer science #Mobile computing #Working environment noise #Databases
Recognition of negative emotions from the speech signal
- Trang 240-243
This paper reports on methods for automatic classification of spoken utterances
based on the emotional state of the speaker. The data set used for the analysis
comes from a corpus of human-machine dialogues recorded from a commercial
application deployed by SpeechWorks. Linear discriminant classification with
Gaussian class-conditional probability distribution and k-nearest neighbors
methods are u...
#Emotion recognition #Speech recognition #Principal component analysis #Automatic speech recognition #Speech analysis #Man machine systems #Linear discriminant analysis #Probability distribution #Statistical distributions #Frequency
Improvement of non-negative matrix factorization based language model using exponential models
- Trang 190-193
This paper describes the use of exponential models to improve non-negative
matrix factorization (NMF) based topic language models for automatic speech
recognition. This modeling technique borrows the basic idea from latent semantic
analysis (LSA), which is typically used in information retrieval. An improvement
was achieved when exponential models were used to estimate the a posteriori
topic proba...
#History #Vectors #Natural languages #Automatic speech recognition #Information analysis #Information retrieval #Singular value decomposition #Training data #Parameter estimation #Iterative algorithms
A one-pass decoder based on polymorphic linguistic context assignment
- Trang 214-217
In this study, we examine how fast decoding of conversational speech with large
vocabularies profits from efficient use of linguistic information, i.e. language
models and grammars. Based on a re-entrant single pronunciation prefix tree, we
use the concept of linguistic context polymorphism to allow an early
incorporation of language model information. This approach allows us to use all
available ...
#Decoding #Context modeling #Automatic speech recognition #Vocabulary #Acoustic beams #Speech recognition #History #Interactive systems #Laboratories #Natural languages
A language model adaptation using multiple varied corpora
- Trang 389-392
A new language model adaptation scheme is proposed to cope with multiple varied
speech recognition tasks. Both topic difference and sentence style difference
resulting from the speaker's role are reflected in the proposed language model
adaptation. An adaptation is carried out using two different language corpora
where only the topic or speaker's style is matched. New word clustering
techniques ar...
#Adaptation model #Natural languages #Speech recognition #Data mining #Frequency #Error analysis #Vocabulary
Verification of multi-class recognition decision using classification approach
- Trang 123-126
We investigate various strategies to improve the utterance verification
performance using a 2-class pattern classifier. They include utilizing N-best
candidate scores, modifying segmentation boundaries, applying background and
out-of-vocabulary filler models, incorporating contexts, and minimizing
verification errors via discriminative training. A connected-digit database
containing utterances rec...
#Testing #Automatic speech recognition #Natural languages #Context modeling #Databases #Microphones #Performance evaluation #Man machine systems #Degradation #Working environment noise
CORBA-based speech-to-speech translation system
- Trang 355-358
We describe the new implementation of a speech-to-speech translation system at
ATR Spoken Language Translation Research Laboratories (SLT). We use the
architecture standard CORBA (Common Object Request Broker Architecture) to
interface between a speech recognizer, translation system and TTS engine.
Various input types are supported, including close-talking microphone and
telephony hardware.
#Speech recognition #Natural languages #Computer architecture #Communication standards #Access protocols #Speech synthesis #Standards development #Standards publication #Network servers #Web server
An examination of three classes of ASR dialogue systems: PC-based dictation, in-car systems and automated directory assistance
- Trang 455-461
Three classes of practical speech recognition dialogue systems are considered,
starting with PC-based systems, specifically dictation systems. Although such
systems have become very effective, they have not achieved mainstream use. Some
reasons for this disappointing outcome are proposed. Speech recognition is now
appearing in production cars. It is argued that the two most attractive in-car
appli...
#Automatic speech recognition #Speech recognition #Marketing and sales #Navigation #Telephony #Databases #Business #Application software #Computerized monitoring #Automatic control
Natural language call routing: towards combination and boosting of classifiers
- Trang 202-205
We describe different techniques to improve natural language call routing:
boosting, relevance feedback, discriminative training, and constrained
minimization. Their common goal is to reweight the data in order to let the
system focus on documents judged hard to classify by a single classifier. These
approaches are evaluated with the common vector-based classifier and also with
the beta classifier...
#Natural languages #Routing #Boosting #Electronic mail #Feedback #Humans #Frequency #Training data #Automatic testing #Information retrieval