1 |
BERT-based Semantic Model for Rescoring N-best Speech Recognition List
|
|
|
|
In: INTERSPEECH 2021 ; https://hal.archives-ouvertes.fr/hal-03248881 ; INTERSPEECH 2021, Aug 2021, Brno, Czech Republic ; https://www.interspeech2021.org/ (2021)
|
|
BASE
|
|
Show details
|
|
2 |
Introduction of semantic model to help speech recognition
|
|
|
|
In: TSD 2020 - Twenty-third International Conference on Text, Speech and Dialogue ; https://hal.archives-ouvertes.fr/hal-02862245 ; TSD 2020 - Twenty-third International Conference on Text, Speech and Dialogue, Sep 2020, Brno, Czech Republic (2020)
|
|
BASE
|
|
Show details
|
|
3 |
Emoción, percepción, producción: un estudio psicolingüístico para detectar emociones en el habla
|
|
|
|
BASE
|
|
Show details
|
|
4 |
"Grumpy" or "furious"? arousal of emotion labels influences judgments of facial expressions
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Combining speech-based and linguistic classifiers to recognize emotion in user spoken utterances
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Speech Perception: Phonological Neighborhood Effects on Word Recognition Persist Despite Semantic Sentence Context
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Inferring Availability for Communication in Smart Homes Using Context
|
|
|
|
In: PerCom 2018 - IEEE International Conference on Pervasive Computing and Communications ; https://hal.archives-ouvertes.fr/hal-01762137 ; PerCom 2018 - IEEE International Conference on Pervasive Computing and Communications, Mar 2018, Athènes, Greece. pp.1-6 (2018)
|
|
BASE
|
|
Show details
|
|
8 |
Automatic Recognition of Affective Laughter in Spontaneous Dyadic Interactions from Audiovisual Signals
|
|
|
|
In: International Conference on Multimodal Interaction (ICMI 2018) ; https://hal.archives-ouvertes.fr/hal-01994000 ; International Conference on Multimodal Interaction (ICMI 2018), Oct 2018, Boulder, CO, United States. pp.220-228, ⟨10.1145/3242969.3243012⟩ (2018)
|
|
BASE
|
|
Show details
|
|
9 |
A developmental perspective on processing semantic context: preliminary evidence from sentential auditory word repetition in school-aged children
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Modelling Semantic Context of OOV Words in Large Vocabulary Continuous Speech Recognition
|
|
|
|
In: ISSN: 2329-9290 ; EISSN: 2329-9304 ; IEEE/ACM Transactions on Audio, Speech and Language Processing ; https://hal.inria.fr/hal-01461617 ; IEEE/ACM Transactions on Audio, Speech and Language Processing, Institute of Electrical and Electronics Engineers, 2017, 25 (3), pp.598 - 610. ⟨10.1109/TASLP.2017.2651361⟩ (2017)
|
|
BASE
|
|
Show details
|
|
11 |
Word Recognition in High and Low Skill Spellers: Context effects on Lexical Ambiguity Resolution
|
|
|
|
In: http://rave.ohiolink.edu/etdc/view?acc_num=kent1493035902158255 (2017)
|
|
BASE
|
|
Show details
|
|
14 |
Learning Spatial-Semantic Context with Fully Convolutional Recurrent Network for Online Handwritten Chinese Text Recognition
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Lightweight Spoken Utterance Classification with CFG, tf-idf and Dynamic Programming
|
|
|
|
In: ISBN: 978-3-319-68455-0 ; Statistical Language and Speech Processing (SLSP) pp. 143-154 (2017)
|
|
BASE
|
|
Show details
|
|
16 |
Recurrent neural network language models for automatic speech recognition
|
|
|
|
Abstract:
The goal of this thesis is to advance the use of recurrent neural network language models (RNNLMs) for large vocabulary continuous speech recognition (LVCSR). RNNLMs are currently state-of-the-art and shown to consistently reduce the word error rates (WERs) of LVCSR tasks when compared to other language models. In this thesis we propose various advances to RNNLMs. The advances are: improved learning procedures for RNNLMs, enhancing the context, and adaptation of RNNLMs. We learned better parameters by a novel pre-training approach and enhanced the context using prosody and syntactic features. We present a pre-training method for RNNLMs, in which the output weights of a feed-forward neural network language model (NNLM) are shared with the RNNLM. This is accomplished by first fine-tuning the weights of the NNLM, which are then used to initialise the output weights of an RNNLM with the same number of hidden units. To investigate the effectiveness of the proposed pre-training method, we have carried out text-based experiments on the Penn Treebank Wall Street Journal data, and ASR experiments on the TED lectures data. Across the experiments, we observe small but significant improvements in perplexity (PPL) and ASR WER. Next, we present unsupervised adaptation of RNNLMs. We adapted the RNNLMs to a target domain (topic or genre or television programme (show)) at test time using ASR transcripts from first pass recognition. We investigated two approaches to adapt the RNNLMs. In the first approach the forward propagating hidden activations are scaled - learning hidden unit contributions (LHUC). In the second approach we adapt all parameters of RNNLM.We evaluated the adapted RNNLMs by showing the WERs on multi genre broadcast speech data. We observe small (on an average 0.1% absolute) but significant improvements in WER compared to a strong unadapted RNNLM model. Finally, we present the context-enhancement of RNNLMs using prosody and syntactic features. The prosody features were computed from the acoustics of the context words and the syntactic features were from the surface form of the words in the context. We trained the RNNLMs with word duration, pause duration, final phone duration, syllable duration, syllable F0, part-of-speech tag and Combinatory Categorial Grammar (CCG) supertag features. The proposed context-enhanced RNNLMs were evaluated by reporting PPL and WER on two speech recognition tasks, Switchboard and TED lectures. We observed substantial improvements in PPL (5% to 15% relative) and small but significant improvements in WER (0.1% to 0.5% absolute).
|
|
Keyword:
adaptation; automatic speech recognition; CCG Supertags; context-enhancement; language modelling; LHUC; MGB Challenge; N-grams; NNLM; POS; pre-training; prosody features; RNNLM; switchboard; syntactic features; TED Talks
|
|
URL: http://hdl.handle.net/1842/28990
|
|
BASE
|
|
Hide details
|
|
17 |
Investigation of Back-off Based Interpolation Between Recurrent Neural Network and N-gram Language Models (Author's Manuscript)
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Insight through uncertainty: a review of the literature on the effects of cognitive processes and schema on responses to elicitation (‘projective’) techniques in evaluation and research interviews
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Introduction to New Work on Immigration and Identity in Contemporary France, Québec, and Ireland
|
|
|
|
In: CLCWeb: Comparative Literature and Culture (2016)
|
|
BASE
|
|
Show details
|
|
20 |
Thematic Bibliography to New Work on Immigration and Identity in Contemporary France, Québec, and Ireland
|
|
|
|
In: CLCWeb: Comparative Literature and Culture (2016)
|
|
BASE
|
|
Show details
|
|
|
|