Prachi Singh

Indian Institute of Science Bangalore

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Sriram Ganapathy

Indian Institute of Science Bangalore

Rajat Varma

Indian Institute of Science Bangalore

Venkat Krishnamohan

University of California, San Diego

Shreyas Ramoji

Indian Institute of Science Bangalore

Harsha Vardhan

Koneru Lakshmaiah Education Foundation

Bhargavram Mysore

North Carolina State University

Mark Liberman

University of Pennsylvania

Christopher Cieri

University of Pennsylvania

Kenneth Church

Northeastern University

Neville Ryant

University of Pennsylvania

Cooperative Institutions

Indian Institute of Science Bangalore

University of Pennsylvania

Pennsylvania Academic Library Consortium

Atal Bihari Vajpayee Indian Institute of Information Technology and Management

Queensland University of Technology

Google (United States)

Authorised Association Consortium

Humboldt-Universität zu Berlin

Washington University in St. Louis

Banaras Hindu University

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Deep Self-Supervised Hierarchical Clustering for Speaker Diarization

Interspeech 2022 (2020)

Prachi Singh Sriram Ganapathy

The state-of-the-art speaker diarization systems use agglomerative hierarchical clustering (AHC) which performs the clustering of previously learned neural embeddings.While the clustering approach attempts to identify speaker clusters, the AHC algorithm does not involve any further learning.In this paper, we propose a novel algorithm for hierarchical clustering which combines the speaker clustering along with a representation learning framework.The proposed approach is based on principles of self-supervised learning where the self-supervision is derived from the clustering algorithm.The representation learning network is trained with a regularized triplet loss using the clustering solution at the current step while the clustering algorithm uses the deep embeddings from the representation learning step.By combining the self-supervision based representation learning along with the clustering algorithm, we show that the proposed algorithm improves significantly (29% relative improvement) over the AHC algorithm with cosine similarity for a speaker diarization task on CALLHOME dataset.In addition, the proposed approach also improves over the stateof-the-art system with PLDA affinity matrix with 10% relative improvement in DER.

Speaker diarisation

Cosine similarity

Hierarchical clustering

Feature Learning

Representation

10.21437/interspeech.2020-2297

Cite

Citations (5)

Self-Supervised Representation Learning With Path Integral Clustering for Speaker Diarization

IEEE/ACM Transactions on Audio Speech and Language Processing (2021)

Prachi Singh Sriram Ganapathy

Automatic speaker diarization techniques typically involve a two-stage processing approach where audio segments of fixed duration are converted to vector representations in the first stage. This is followed by an unsupervised clustering of the representations in the second stage. In most of the prior approaches, these two stages are performed in an isolated manner with independent optimization steps. In this paper, we propose a representation learning and clustering algorithm that can be iteratively performed for improved speaker diarization. The representation learning is based on principles of self-supervised learning while the clustering algorithm is a graph structural method based on path integral clustering (PIC). The representation learning step uses the cluster targets from PIC and the clustering step is performed on embeddings learned from the self-supervised deep model. This iterative approach is referred to as self-supervised clustering (SSC). The diarization experiments are performed on CALLHOME and AMI meeting datasets. In these experiments, we show that the SSC algorithm improves significantly over the baseline system (relative improvements of 13% and 59% on CALLHOME and AMI datasets respectively in terms of diarization error rate (DER)). In addition, the DER results reported in this work improve over several other recent approaches for speaker diarization.

Speaker diarisation

Representation

Feature Learning

10.1109/taslp.2021.3075100

Cite

Citations (6)

Pairwise Discriminative Neural PLDA for Speaker Verification.

arXiv (Cornell University) (2020)

Shreyas Ramoji Prashant Krishnan Prachi Singh Sriram Ganapathy

The state-of-art approach to speaker verification involves the extraction of discriminative embeddings like x-vectors followed by a generative model back-end using a probabilistic linear discriminant analysis (PLDA). In this paper, we propose a Pairwise neural discriminative model for the task of speaker verification which operates on a pair of speaker embeddings such as x-vectors/i-vectors and outputs a score that can be considered as a scaled log-likelihood ratio. We construct a differentiable cost function which approximates speaker verification loss, namely the minimum detection cost. The pre-processing steps of linear discriminant analysis (LDA), unit length normalization and within class covariance normalization are all modeled as layers of a neural model and the speaker verification cost functions can be back-propagated through these layers during training. We also explore regularization techniques to prevent overfitting, which is a major concern in using discriminative back-end models for verification tasks. The experiments are performed on the NIST SRE 2018 development and evaluation datasets. We observe average relative improvements of 8% in CMN2 condition and 30% in VAST condition over the PLDA baseline system.

Discriminative model

Normalization

NIST

Overfitting

Speaker Verification

Source

Cite

Citations (4)

LEAP System for SRE 2019 CTS Challenge - Improvements and Error Analysis

Shreyas Ramoji Prashant Krishnan Bhargavram Mysore Prachi Singh Sriram Ganapathy

The NIST Speaker Recognition Evaluation - Conversational Telephone Speech (CTS) challenge 2019 was an open evaluation for the task of speaker verification in challenging conditions. In this paper, we provide a detailed account of the LEAP SRE system submitted to the CTS challenge focusing on the novel components in the back-end system modeling. All the systems used the time-delay neural network (TDNN) based x-vector embeddings. The x-vector system in our SRE19 submission used a large pool of training speakers (about 14k speakers). Following the x-vector extraction, we explored a neural network approach to backend score computation that was optimized for a speaker verification cost. The system combination of generative and neural PLDA models resulted in significant improvements for the SRE evaluation dataset. We also found additional gains for the SRE systems based on score normalization and calibration. Subsequent to the evaluations, we have performed a detailed analysis of the submitted systems. The analysis revealed the incremental gains obtained for different training dataset combinations as well as the modeling methods.

NIST

Normalization

Speaker Verification

10.21437/odyssey.2020-40

Cite

Citations (4)

LEAP Submission for the Third DIHARD Diarization Challenge

arXiv (Cornell University) (2021)

Prachi Singh Rajat Varma Venkat Krishnamohan Srikanth Raj Chetupalli Sriram Ganapathy

The LEAP submission for DIHARD-III challenge is described in this paper. The proposed system is composed of a speech bandwidth classifier, and diarization systems fine-tuned for narrowband and wideband speech separately. We use an end-to-end speaker diarization system for the narrowband conversational telephone speech recordings. For the wideband multi-speaker recordings, we use a neural embedding based clustering approach, similar to the baseline system. The embeddings are extracted from a time-delay neural network (called x-vectors) followed by the graph based path integral clustering (PIC) approach. The LEAP system showed 24% and 18% relative improvements for Track-1 and Track-2 respectively over the baseline system provided by the organizers. This paper describes the challenge submission, the post-evaluation analysis and improvements observed on the DIHARD-III dataset.

Narrowband

Speaker diarisation

Wideband

Baseline (sea)

Wideband audio

Source

Cite

Citations (0)

A Review On Face Emotion Recognition Techniques

International Journal of Scientific Research in Computer Science Engineering and Information Technology (2019)

Pamela Vinitha Eric Pooja Nimje Roshlin Acharya Prachi Singh

10.32628/cseit1949124

Cite

Citations (0)

The Leap Speaker Recognition System for NIST SRE 2018 Challenge

ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2019)

Shreyas Ramoji Anand Mohan Bhargavram Mysore Anmol Bhatia Prachi Singh

The NIST Speaker Recognition Evaluation (SRE) 2018 challenge comprises an open evaluation of the text independent speaker verification task. This paper summarizes the LEAP speaker verification systems submitted to the NIST SRE 2018. For all the speaker verification approaches, the front-end feature extraction involved the use of neural embeddings from a time delay neural network (TDNN) trained on a speaker discrimination task. These features, called x-vectors, are used in multiple ways for speaker verification task. In the first approach, the x-vectors with pre-processing and dimensionality reduction, are used with probabilistic linear discriminant analysis (PLDA) scoring. The second approach applies a speaker diarization scheme on the test segments containing multiple talkers before speaker verification scoring based on PLDA. The third system uses a local pairwise LDA model for pre-processing the x-vectors which are then scored using a Gaussian back-end. With experiments on the SRE 2018 database, we show that most of the systems achieved noticeable improvements over the NIST baseline in terms of the primary cost metric. Using a system fusion of the various approaches, we obtain significant improvements over the NIST official baseline (average relative improvements of 19.7% and 20.1% for the development and evaluation set respectively).

NIST

Speaker diarisation

10.1109/icassp.2019.8683148

Cite

Citations (8)

The Third DIHARD Diarization Challenge

arXiv (Cornell University) (2020)

Neville Ryant Prachi Singh Venkat Krishnamohan Rajat Varma Kenneth Church

DIHARD III was the third in a series of speaker diarization challenges intended to improve the robustness of diarization systems to variability in recording equipment, noise conditions, and conversational domain. Speaker diarization was evaluated under two speech activity conditions (diarization from a reference speech activity vs. diarization from scratch) and 11 diverse domains. The domains span a range of recording conditions and interaction types, including read audio-books, meeting speech, clinical interviews, web videos, and, for the first time, conversational telephone speech. A total of 30 organizations (forming 21teams) from industry and academia submitted 499 valid system outputs. The evaluation results indicate that speaker diarization has improved markedly since DIHARD I, particularly for two-party interactions, but that for many domains (e.g., web video) the problem remains far from solved.

Speaker diarisation

Robustness

Transcription

Source

Cite

Citations (21)

Overlap-aware End-to-End Supervised Hierarchical Graph Clustering for Speaker Diarization

arXiv (Cornell University) (2024)

Prachi Singh Sriram Ganapathy

Speaker diarization, the task of segmenting an audio recording based on speaker identity, constitutes an important speech pre-processing step for several downstream applications. The conventional approach to diarization involves multiple steps of embedding extraction and clustering, which are often optimized in an isolated fashion. While end-to-end diarization systems attempt to learn a single model for the task, they are often cumbersome to train and require large supervised datasets. In this paper, we propose an end-to-end supervised hierarchical clustering algorithm based on graph neural networks (GNN), called End-to-end Supervised HierARchical Clustering (E-SHARC). The E-SHARC approach uses front-end mel-filterbank features as input and jointly learns an embedding extractor and the GNN clustering module, performing representation learning, metric learning, and clustering with end-to-end optimization. Further, with additional inputs from an external overlap detector, the E-SHARC approach is capable of predicting the speakers in the overlapping speech regions. The experimental evaluation on several benchmark datasets like AMI, VoxConverse and DISPLACE, illustrates that the proposed E-SHARC framework improves significantly over the state-of-art diarization systems.

Speaker diarisation

Benchmark (surveying)

End-to-end principle

Hierarchical clustering

10.48550/arxiv.2401.12850

Cite

Citations (0)

End-to-End Supervised Hierarchical Graph Clustering for Speaker Diarization

IEEE Transactions on Audio Speech and Language Processing (2025)

Prachi Singh Sriram Ganapathy

Speaker diarisation

End-to-end principle

Hierarchical clustering

10.1109/taslpro.2025.3525967

Cite

Citations (0)