3 |
Using Automatic Speech Recognition to Optimize Hearing-Aid Time Constants
|
|
|
|
In: ISSN: 1662-4548 ; EISSN: 1662-453X ; Frontiers in Neuroscience ; https://hal.archives-ouvertes.fr/hal-03627441 ; Frontiers in Neuroscience, Frontiers, 2022, 16 (779062), ⟨10.3389/fnins.2022.779062⟩ ; https://www.frontiersin.org/articles/10.3389/fnins.2022.779062/full (2022)
|
|
BASE
|
|
Show details
|
|
4 |
RETRIEVING SPEAKER INFORMATION FROM PERSONALIZED ACOUSTIC MODELS FOR SPEECH RECOGNITION
|
|
|
|
In: IEEE ICASSP 2022 ; https://hal.archives-ouvertes.fr/hal-03539741 ; IEEE ICASSP 2022, 2022, Singapour, Singapore (2022)
|
|
Abstract:
International audience ; The widespread of powerful personal devices capable of collecting voice of their users has opened the opportunity to build speaker adapted speech recognition system (ASR) or to participate to collaborative learning of ASR. In both cases, personalized acoustic models (AM), i.e. fine-tuned AM with specific speaker data, can be built. A question that naturally arises is whether the dissemination of personalized acoustic models can leak personal information. In this paper, we show that it is possible to retrieve the gender of the speaker, but also his identity, by just exploiting the weight matrix changes of a neural acoustic model locally adapted to this speaker. Incidentally we observe phenomena that may be useful towards explainability of deep neural networks in the context of speech processing. Gender can be identified almost surely using only the first layers and speaker verification performs well when using middle-up layers. Our experimental study on the TED-LIUM 3 dataset with HMM/TDNN models shows an accuracy of 95% for gender detection, and an Equal Error Rate of 9.07% for a speaker verification task by only exploiting the weights from personalized models that could be exchanged instead of user data.
|
|
Keyword:
[INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]; acoustic model; Automatic speech recognition; collaborative learning; personalized acoustic models; speaker information
|
|
URL: https://hal.archives-ouvertes.fr/hal-03539741 https://hal.archives-ouvertes.fr/hal-03539741/document https://hal.archives-ouvertes.fr/hal-03539741/file/ICASSP_2022_SpeakerAnalysisInfoPrivacyVF.pdf
|
|
BASE
|
|
Hide details
|
|
5 |
Emotional Speech Recognition Using Deep Neural Networks
|
|
|
|
In: ISSN: 1424-8220 ; Sensors ; https://hal.archives-ouvertes.fr/hal-03632853 ; Sensors, MDPI, 2022, 22 (4), pp.1414. ⟨10.3390/s22041414⟩ (2022)
|
|
BASE
|
|
Show details
|
|
6 |
The Impact of Removing Head Movements on Audio-visual Speech Enhancement
|
|
|
|
In: ICASSP 2022 - IEEE International Conference on Acoustics, Speech and Signal Processing ; https://hal.inria.fr/hal-03551610 ; ICASSP 2022 - IEEE International Conference on Acoustics, Speech and Signal Processing, IEEE Signal Processing Society, May 2022, Singapore, Singapore. pp.1-5 (2022)
|
|
BASE
|
|
Show details
|
|
8 |
Efficient localization of the cortical language network and its functional neuroanatomy in dyslexia
|
|
|
|
BASE
|
|
Show details
|
|
9 |
How are visemes and graphemes integrated with speech sounds during spoken word recognition? ERP evidence for supra-additive responses during audiovisual compared to auditory speech processing
|
|
|
|
In: ISSN: 0093-934X ; EISSN: 1090-2155 ; Brain and Language ; https://hal.archives-ouvertes.fr/hal-03472191 ; Brain and Language, Elsevier, 2022, 225, ⟨10.1016/j.bandl.2021.105058⟩ (2022)
|
|
BASE
|
|
Show details
|
|
10 |
Multistream neural architectures for cued-speech recognition using a pre-trained visual feature extractor and constrained CTC decoding
|
|
|
|
In: ICASSP 2022 - IEEE International Conference on Acoustics, Speech and Signal Processing ; https://hal.archives-ouvertes.fr/hal-03578503 ; ICASSP 2022 - IEEE International Conference on Acoustics, Speech and Signal Processing, May 2022, Singapour, Singapore (2022)
|
|
BASE
|
|
Show details
|
|
11 |
Multistream neural architectures for cued-speech recognition using a pre-trained visual feature extractor and constrained CTC decoding
|
|
|
|
In: ICASSP 2022 - IEEE International Conference on Acoustics, Speech and Signal Processing ; https://hal.archives-ouvertes.fr/hal-03578503 ; ICASSP 2022 - IEEE International Conference on Acoustics, Speech and Signal Processing, May 2022, Singapour, Singapore (2022)
|
|
BASE
|
|
Show details
|
|
12 |
Hippocampal and auditory contributions to speech segmentation
|
|
|
|
In: ISSN: 0010-9452 ; Cortex ; https://hal.archives-ouvertes.fr/hal-03604957 ; Cortex, Elsevier, 2022, ⟨10.1016/j.cortex.2022.01.017⟩ (2022)
|
|
BASE
|
|
Show details
|
|
13 |
Speech Perception and Implementation in a Virtual Medical Assistant
|
|
|
|
In: 6. ICAART – 14th International Conference on Agents and Artificial Intelligence ; https://hal.archives-ouvertes.fr/hal-03621550 ; 6. ICAART – 14th International Conference on Agents and Artificial Intelligence, Feb 2022, Vienna, Austria (2022)
|
|
BASE
|
|
Show details
|
|
14 |
Évaluation de la perception des sons de parole chez les populations pédiatriques : réflexion sur les épreuves existantes
|
|
|
|
In: ISSN: 0298-6477 ; EISSN: 2117-7155 ; Glossa ; https://hal.archives-ouvertes.fr/hal-03646757 ; Glossa, UNADREO - Union NAtionale pour le Développement de la Recherche en Orthophonie, 2022, 132, pp.1-27 ; https://www.glossa.fr/index.php/glossa/article/view/1043 (2022)
|
|
BASE
|
|
Show details
|
|
15 |
Automatic generation of the complete vocal tract shape from the sequence of phonemes to be articulated
|
|
|
|
In: ISSN: 0167-6393 ; EISSN: 1872-7182 ; Speech Communication ; https://hal.univ-lorraine.fr/hal-03650212 ; Speech Communication, Elsevier : North-Holland, 2022, ⟨10.1016/j.specom.2022.04.004⟩ (2022)
|
|
BASE
|
|
Show details
|
|
16 |
Cross-lingual few-shot hate speech and offensive language detection using meta learning
|
|
|
|
In: ISSN: 2169-3536 ; EISSN: 2169-3536 ; IEEE Access ; https://hal.archives-ouvertes.fr/hal-03559484 ; IEEE Access, IEEE, 2022, 10, pp.14880-14896. ⟨10.1109/ACCESS.2022.3147588⟩ (2022)
|
|
BASE
|
|
Show details
|
|
17 |
Fine-tuning pre-trained models for Automatic Speech Recognition: experiments on a fieldwork corpus of Japhug (Trans-Himalayan family)
|
|
|
|
In: https://halshs.archives-ouvertes.fr/halshs-03647315 ; 2022 (2022)
|
|
BASE
|
|
Show details
|
|
18 |
Intelligibility and comprehensibility: A Delphi consensus study
|
|
|
|
In: ISSN: 1368-2822 ; EISSN: 1460-6984 ; International Journal of Language and Communication Disorders ; https://hal.archives-ouvertes.fr/hal-03543198 ; International Journal of Language and Communication Disorders, Wiley, 2022, 57 (1), pp.21 - 41. ⟨10.1111/1460-6984.12672⟩ ; https://onlinelibrary.wiley.com/doi/10.1111/1460-6984.12672 (2022)
|
|
BASE
|
|
Show details
|
|
19 |
Vocal size exaggeration may have contributed to the origins of vocalic complexity
|
|
|
|
In: ISSN: 0962-8436 ; EISSN: 1471-2970 ; Philosophical Transactions of the Royal Society B: Biological Sciences ; https://hal.archives-ouvertes.fr/hal-03501105 ; Philosophical Transactions of the Royal Society B: Biological Sciences, Royal Society, The, 2022, 377 (1841), ⟨10.1098/rstb.2020.0401⟩ (2022)
|
|
BASE
|
|
Show details
|
|
20 |
Investigating the locus of transposed-phoneme effects using cross-modal priming
|
|
|
|
In: ISSN: 0001-6918 ; EISSN: 1873-6297 ; Acta Psychologica ; https://hal.archives-ouvertes.fr/hal-03619856 ; Acta Psychologica, Elsevier, 2022, 226, pp.103578. ⟨10.1016/j.actpsy.2022.103578⟩ (2022)
|
|
BASE
|
|
Show details
|
|
|
|