activity
20192022
most citedSpeech denoising by parametric resynthesis

4 citations · 6 across the 4 of their papers we have counts for

collaborators

6 papers

eess.AS20221 cited

SpeechLMScore: Evaluating speech generation using speech language model

Soumi Maiti, Yifan Peng, Takaaki Saeki +1

While human evaluation is the most reliable metric for evaluating speech generation systems, it is generally costly and time-consuming. Previous studies on automatic speech quality…

cs.SD2021

End-to-End Diarization for Variable Number of Speakers with Local-Global Networks and Discriminative Speaker Embeddings

Soumi Maiti, Hakan Erdogan, Kevin Wilson +3

We present an end-to-end deep network model that performs meeting diarization from single-channel audio recordings. End-to-end diarization models have the advantage of handling spe…

cs.CL20201 cited

Generating Multilingual Voices Using Speaker Space Translation Based on Bilingual Speaker Data

Soumi Maiti, Erik Marchi, Alistair Conkie

We present progress towards bilingual Text-to-Speech which is able to transform a monolingual voice to speak a second language while preserving speaker voice quality. We demonstrat…

cs.SD2019

Speaker independence of neural vocoders and their effect on parametric resynthesis speech enhancement

Soumi Maiti, Michael I Mandel

Traditional speech enhancement systems produce speech with compromised quality. Here we propose to use the high quality speech generation capability of neural vocoders for better q…

cs.SD2019

Parametric Resynthesis with neural vocoders

Soumi Maiti, Michael I Mandel

Noise suppression systems generally produce output speech with compromised quality. We propose to utilize the high quality speech generation capability of neural vocoders for noise…

eess.AS20194 cited

Speech denoising by parametric resynthesis

Soumi Maiti, Michael I Mandel

This work proposes the use of clean speech vocoder parameters as the target for a neural network performing speech enhancement. These parameters have been designed for text-to-spee…