1 |
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
|
|
2 |
An Overview of Indian Spoken Language Recognition from Machine Learning Perspective
|
|
|
|
In: ISSN: 2375-4699 ; EISSN: 2375-4702 ; ACM Transactions on Asian and Low-Resource Language Information Processing ; https://hal.inria.fr/hal-03616853 ; ACM Transactions on Asian and Low-Resource Language Information Processing, ACM, In press, ⟨10.1145/3523179⟩ (2022)
|
|
BASE
|
|
Show details
|
|
3 |
Große Hoffnungen, große Hürden : Der Einfluss von bilingualem Lernen im außerschulischen Lernort Labor auf Leistung, Verständnis, Selbstkonzept, und Kreativität ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
The CLASSLA-StanfordNLP model for lemmatisation of standard Slovenian 1.4
|
|
|
|
BASE
|
|
Show details
|
|
5 |
The CLASSLA-StanfordNLP model for morphosyntactic annotation of standard Slovenian 1.3
|
|
|
|
BASE
|
|
Show details
|
|
6 |
A argumentatividade na aula de Português Língua Materna: Uma competência crucial para o desenvolvimento da escrita nos Ensino Básico e Secundário
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Can distributional semantics explain performance on the false belief task? ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Cerebral Polymorphisms for Lateralisation: Modelling the Genetic and Phenotypic Architectures of Multiple Functional Modules
|
|
|
|
In: Symmetry; Volume 14; Issue 4; Pages: 814 (2022)
|
|
BASE
|
|
Show details
|
|
9 |
Detection of Chinese Deceptive Reviews Based on Pre-Trained Language Model
|
|
|
|
In: Applied Sciences; Volume 12; Issue 7; Pages: 3338 (2022)
|
|
BASE
|
|
Show details
|
|
10 |
The Competitive Advantage of the Indian and Korean Film Industries: An Empirical Analysis Using Natural Language Processing Methods
|
|
|
|
In: Applied Sciences; Volume 12; Issue 9; Pages: 4592 (2022)
|
|
BASE
|
|
Show details
|
|
11 |
Stability and Evolution of Synonyms and Homonyms in Signaling Game
|
|
|
|
In: Entropy; Volume 24; Issue 2; Pages: 194 (2022)
|
|
BASE
|
|
Show details
|
|
12 |
Deep Learning-Based End-to-End Language Development Screening for Children Using Linguistic Knowledge
|
|
|
|
In: Applied Sciences; Volume 12; Issue 9; Pages: 4651 (2022)
|
|
BASE
|
|
Show details
|
|
13 |
Cross-Lingual Transfer Learning for Arabic Task-Oriented Dialogue Systems Using Multilingual Transformer Model mT5
|
|
|
|
In: Mathematics; Volume 10; Issue 5; Pages: 746 (2022)
|
|
BASE
|
|
Show details
|
|
14 |
AraConv: Developing an Arabic Task-Oriented Dialogue System Using Multi-Lingual Transformer Model mT5
|
|
|
|
In: Applied Sciences; Volume 12; Issue 4; Pages: 1881 (2022)
|
|
BASE
|
|
Show details
|
|
15 |
Segmental and Prosodic Evidence for Property-by-Property Transfer in L3 English in Northern Africa
|
|
|
|
In: Languages; Volume 7; Issue 1; Pages: 28 (2022)
|
|
BASE
|
|
Show details
|
|
16 |
FORMS AND METHODS IN MODERN APPROACHES TO STUDENT SELF LEARNING ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
FORMS AND METHODS IN MODERN APPROACHES TO STUDENT SELF LEARNING ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
StaResGRU-CNN with CMedLMs: a stacked residual GRU-CNN with pre-trained biomedical language models for predictive intelligence
|
|
|
|
BASE
|
|
Show details
|
|
19 |
THE INFLUENCE OF LINGUISTIC STYLE: A MATCHED-GUISE EXPERIMENT ASSESSING THE EFFECTS OF SOURCE ACCENT, ARGUMENT QUALITY, AND ISSUE INVOLVEMENT ON PERSUASION
|
|
|
|
In: Theses and Dissertations--Communication (2022)
|
|
BASE
|
|
Show details
|
|
20 |
Learning Argument Structures with Recurrent Neural Network Grammars
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2022)
|
|
BASE
|
|
Show details
|
|
|
|