An End-to-end Network to Synthesize Intonation Using a Generalized Command Response Model

Marelli, François; Schnell, Bastian; Bourlard, Hervé; Dutoit, Thierry; Garner, Philip N.

doi:10.1109/icassp.2019.8683815

Cited by 5 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, question intonation across sentences and speakers is very far from homogeneous making learning such forms from a corpus a challenging task. Research in this area is still at an early stage, with the exploration of different neural net models and feature architectures to improve the variation expected in spoken intonation a source of current research [Kenter et al 2019, Marelli et al 2019, Sun et al 2020.…”

Section: Emphasis and Question Intonationmentioning

confidence: 99%

Building and Designing Expressive Speech Synthesis

Aylett¹,

Clark²,

Cowan³

et al. 2021

The Handbook on Socially Interactive Agents

View full text Add to dashboard Cite

You all know the test for artificial intelligence -the Turing test. A human judge has a conversation with a human and a computer. If the judge can't tell the machine apart from the human, the machine has passed the test. I now propose a test for computer voices -the Ebert test. If a computer voice can successfully tell a joke and do the timing and delivery as well as Henny Youngman, then that's the voice I want." -Roger Ebert.

show abstract

Section: Emphasis and Question Intonationmentioning

confidence: 99%

Building and Designing Expressive Speech Synthesis

Aylett¹,

Clark²,

Cowan³

et al. 2021

The Handbook on Socially Interactive Agents

View full text Add to dashboard Cite

show abstract

“…The paper [ 36 ] offers a suggestion for a demonstration to enhance the synthesized speech’s prosody of mathematical markup language (MathML) based mathematical expressions, while [ 37 ] demonstrates that an end-to-end neural network with integrated second-order adaptable linear all-pole digital filters can produce intonation with a natural sound, provided that the proper stability conditions are applied. However, while intonational synthesis speech has come a long way in recent years, it still faces challenges in replicating the full range of natural intonation patterns and nuances of human speech.…”

Section: Related Workmentioning

confidence: 99%

Continuous Sign Language Recognition and Its Translation into Intonation-Colored Speech

Amangeldy

Ukenova

Bekmanova

et al. 2023

Sensors

View full text Add to dashboard Cite

This article is devoted to solving the problem of converting sign language into a consistent text with intonation markup for subsequent voice synthesis of sign phrases by speech with intonation. The paper proposes an improved method of continuous recognition of sign language, the results of which are transmitted to a natural language processor based on analyzers of morphology, syntax, and semantics of the Kazakh language, including morphological inflection and the construction of an intonation model of simple sentences. This approach has significant practical and social significance, as it can lead to the development of technologies that will help people with disabilities to communicate and improve their quality of life. As a result of the cross-validation of the model, we obtained an average test accuracy of 0.97 and an average val_accuracy of 0.90 for model evaluation. We also identified 20 sentence structures of the Kazakh language with their intonational model.

show abstract

“…To this end, we use a DNN-based state-of-the-art Merlin TTS system in conjunction with the Festival front-end, two Bidirectional Long Short-Term Memory networks as duration and acoustic models, and the WORLD vocoder. For details on the TTS systems and the training procedure, the reader is referred to [23,24]. By training a TTS system for each speaker, we get 4 speaker-dependent TTS systems.…”

Section: Algorithmic Settings Evaluation and State-of-the-art Measuresmentioning

confidence: 99%

Synthetic Speech References for Automatic Pathological Speech Intelligibility Assessment

Janbakhshi

Kodrasi

Bourlard

2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

Automatic pathological speech intelligibility measures are crucial to assist the clinical diagnosis and treatment of speech disorders. The recently proposed pathological short-time objective intelligibility (P-ESTOI) measure was shown to be very advantageous, yielding a high performance for several speech pathologies. However, to assess the intelligibility of an utterance from a patient, P-ESTOI relies on the availability of recordings of the same utterance by several healthy speakers such that an intelligible reference model can be created. Such recordings are not always easily available, limiting the practical applicability of P-ESTOI. To be able to use P-ESTOI in such scenarios, in this paper we propose to use synthetic speech generated by state-of-the-art high-quality text-to-speech systems to create an intelligible reference model. Experimental results on a database of Cerebral Palsy patients show that the performance of P-ESTOI using synthetic speech references is comparable to using natural speech references, making P-ESTOI a flexible measure which does not require healthy speech recordings and which outperforms state-of-the-art pathological speech intelligibility measures.

show abstract

An End-to-end Network to Synthesize Intonation Using a Generalized Command Response Model

Cited by 5 publications

References 17 publications

Building and Designing Expressive Speech Synthesis

Building and Designing Expressive Speech Synthesis

Continuous Sign Language Recognition and Its Translation into Intonation-Colored Speech

Synthetic Speech References for Automatic Pathological Speech Intelligibility Assessment

Contact Info

Product

Resources

About