2 |
YAST : A scalable ASR toolkit especially designed for under-resourced languages
|
|
|
|
In: International Conference onAsian Language Processing (IALP) ; https://hal.archives-ouvertes.fr/hal-01315532 ; International Conference onAsian Language Processing (IALP), Nov 2012, Hanoi, Vietnam. ⟨10.1109/IALP.2012.65⟩ (2012)
|
|
BASE
|
|
Show details
|
|
3 |
Acoustic modeling for under-resourced languages based on vectorial HMM-states representation using Subspace Gaussian Mixture Models
|
|
|
|
In: IEEE Spoken Language Technology Workshop (SLT) ; https://hal.archives-ouvertes.fr/hal-01313103 ; IEEE Spoken Language Technology Workshop (SLT), Dec 2012, Miami, United States. ⟨10.1109/SLT.2012.6424245⟩ (2012)
|
|
Abstract:
International audience ; This paper explores a novel method for context-dependent models in automatic speech recognition (ASR), in the context of under-resourced languages. We present a simple way to realize a tying states approach, based on a new vectorial representation of the HMM states. This vectorial representation is considered as a vector of a low number of parameters obtained by the Subspace Gaussian Mixture Models paradigm (SGMM). The proposed method does not require phonetic knowledge or a large amount of data, which represent the major problems of acoustic modeling for under-resourced languages. This paper shows how this representation can be obtained and used for tying states. Our experiments, applied on Vietnamese, show that this approach achieves a stable gain compared to the classical approach which is based on decision trees. Furthermore, this method appears to be portable to other languages, as shown in the preliminary study conducted on Berber.
|
|
Keyword:
[INFO]Computer Science [cs]; HMM-state vector representation; Index Terms— Acoustic Modelling; state-tying; Subspace Gaussian Mixture Models; under-resourced languages
|
|
URL: https://hal.archives-ouvertes.fr/hal-01313103 https://doi.org/10.1109/SLT.2012.6424245
|
|
BASE
|
|
Hide details
|
|
4 |
Enrichissement dynamique du vocabulairè a partir du Web
|
|
|
|
In: JEP ; https://hal.archives-ouvertes.fr/hal-01319845 ; JEP, Jun 2008, Avignon, France (2008)
|
|
BASE
|
|
Show details
|
|
5 |
On-demand new word learning using world wide web
|
|
|
|
In: IEEE International Conference on Acoustics, Speech and Signal Processing ; https://hal.archives-ouvertes.fr/hal-01319857 ; IEEE International Conference on Acoustics, Speech and Signal Processing , Mar 2008, Las Vegas, United States. ⟨10.1109/ICASSP.2008.4518607⟩ (2008)
|
|
BASE
|
|
Show details
|
|
6 |
Reconnaissance de la parole continue à grand vocabulaire en vietnamien, une langue syllabique tonale
|
|
|
|
In: Les Journées d’Etude sur la Parole (JEP) ; https://hal.archives-ouvertes.fr/hal-01314293 ; Les Journées d’Etude sur la Parole (JEP), Jun 2008, Avignon, France (2008)
|
|
BASE
|
|
Show details
|
|
7 |
LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION FOR VIETNAMESE, A UNDER-RESOURCED LANGUAGE
|
|
|
|
In: The first International Workshop on Spoken Languages Technologies for Under-resourced languages (SLTU - 2008) ; https://hal.archives-ouvertes.fr/hal-01311389 ; The first International Workshop on Spoken Languages Technologies for Under-resourced languages (SLTU - 2008), 2008, Hanoi, Vietnam (2008)
|
|
BASE
|
|
Show details
|
|
8 |
The LIA Speech Recognition System: From 10xRT to 1xRT
|
|
|
|
In: 10th International Conference, TSD ; https://hal.archives-ouvertes.fr/hal-01318280 ; 10th International Conference, TSD , Sep 2007, Pilsen, Czech Republic (2007)
|
|
BASE
|
|
Show details
|
|
9 |
The LIA Speech Recognition System: From 10xRT to 1xRT
|
|
|
|
In: 10th International Conference, TSD ; https://hal.archives-ouvertes.fr/hal-01318314 ; 10th International Conference, TSD, Sep 2007, Pilsen, Czech Republic (2007)
|
|
BASE
|
|
Show details
|
|
10 |
A SCALABLE SYSTEM FOR EMBEDDED LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION
|
|
|
|
In: 15th International Conference on Digital Signal Processing (DSP) ; https://hal.archives-ouvertes.fr/hal-01318263 ; 15th International Conference on Digital Signal Processing (DSP), Jul 2007, Cardiff, United Kingdom (2007)
|
|
BASE
|
|
Show details
|
|
11 |
Imperfect transcript driven speech recognition
|
|
|
|
In: INTERSPEECH ; https://hal.archives-ouvertes.fr/hal-01318085 ; INTERSPEECH, Sep 2006, Pittsburgh, United States (2006)
|
|
BASE
|
|
Show details
|
|
12 |
Reducing computational and memory cost for cellular phone embedded speech recognition system
|
|
|
|
In: IEEE International Conference on Acoustics, Speech, and Signal Processing. (ICASSP '04). ; https://hal.archives-ouvertes.fr/hal-01318230 ; IEEE International Conference on Acoustics, Speech, and Signal Processing. (ICASSP '04)., May 2004, Montreal, Canada. ⟨10.1109/ICASSP.2004.1327109⟩ (2004)
|
|
BASE
|
|
Show details
|
|
13 |
Principes et performances du décodeur parole continue Speeral
|
|
|
|
In: JEP ; https://hal.archives-ouvertes.fr/hal-01319843 ; JEP, Jun 2002, Nancy, France (2002)
|
|
BASE
|
|
Show details
|
|
|
|