Search Results for author: Sri Harsha Dumpala

Found 8 papers, 0 papers with code

Test-Time Training for Speech

no code implementations19 Sep 2023 Sri Harsha Dumpala, Chandramouli Sastry, Sageev Oore

In this paper, we study the application of Test-Time Training (TTT) as a solution to handling distribution shifts in speech applications.

Speaker Identification

Training Diffusion Classifiers with Denoising Assistance

no code implementations15 Jun 2023 Chandramouli Sastry, Sri Harsha Dumpala, Sageev Oore

Score-matching and diffusion models have emerged as state-of-the-art generative models for both conditional and unconditional generation.

Denoising

Musical Speech: A Transformer-based Composition Tool

no code implementations2 Aug 2021 Jason d'Eon, Sri Harsha Dumpala, Chandramouli Shama Sastry, Dani Oore, Sageev Oore

In this paper, we propose a new compositional tool that will generate a musical outline of speech recorded/provided by the user for use as a musical building block in their compositions.

Significance of Speaker Embeddings and Temporal Context for Depression Detection

no code implementations24 Jul 2021 Sri Harsha Dumpala, Sebastian Rodriguez, Sheri Rempel, Rudolf Uher, Sageev Oore

In this work, we analyze the significance of speaker embeddings for the task of depression detection from speech.

Depression Detection

A Cycle-GAN Approach to Model Natural Perturbations in Speech for ASR Applications

no code implementations18 Dec 2019 Sri Harsha Dumpala, Imran Sheikh, Rupayan Chakraborty, Sunil Kumar Kopparapu

Naturally introduced perturbations in audio signal, caused by emotional and physical states of the speaker, can significantly degrade the performance of Automatic Speech Recognition (ASR) systems.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Sentiment Analysis using Imperfect Views from Spoken Language and Acoustic Modalities

no code implementations WS 2018 Imran Sheikh, Sri Harsha Dumpala, Rupayan Chakraborty, Sunil Kumar Kopparapu

Multimodal sentiment classification in practical applications may have to rely on erroneous and imperfect views, namely (a) language transcription from a speech recognizer and (b) under-performing acoustic views.

Automatic Speech Recognition (ASR) General Classification +2

A Novel Approach for Effective Learning in Low Resourced Scenarios

no code implementations15 Dec 2017 Sri Harsha Dumpala, Rupayan Chakraborty, Sunil Kumar Kopparapu

Deep learning based discriminative methods, being the state-of-the-art machine learning techniques, are ill-suited for learning from lower amounts of data.

BIG-bench Machine Learning Classification +2

k-FFNN: A priori knowledge infused Feed-forward Neural Networks

no code implementations24 Apr 2017 Sri Harsha Dumpala, Rupayan Chakraborty, Sunil Kumar Kopparapu

It is not immediately clear (a) how a priori temporal knowledge can be used in a FFNN architecture (b) how a FFNN performs when provided with this knowledge about temporal correlations (assuming available) during training.

Cannot find the paper you are looking for? You can Submit a new open access paper.