arXiv subjects

Shashi Kumar

Publications and source records attributed to Shashi Kumar.

27 records · Page 2Linked to original sources

arXiv2025

Efficient Data Selection for Domain Adaptation of ASR Using Pseudo-Labels and Multi-Stage Filtering

Fine-tuning pretrained ASR models for specific domains is challenging for small organizations with limited labeled data and computational resources. Here, we explore different data selection pipelines and propose a robust approach that improves ASR adaptation by filtering pseudo-labels generated using Whisper (encoder-decoder) and Zipformer (transducer) models. Our approach integrates multiple selection strategies -- including word error rate (WER) prediction, named entity recognition (NER), and character error rate (CER) analysis -- to extract high-quality training segments. We evaluate our method on Whisper and Zipformer using a 7500-hour baseline, comparing it to a CER-based approach relying on hypotheses from three ASR systems. Fine-tuning on 7500 hours of pseudo-labeled call center data achieves 12.3% WER, while our filtering reduces the dataset to 100 hours (1.4%) with similar performance; a similar trend is observed on Fisher English.

cs.CL↗

arXiv2025

Performance evaluation of SLAM-ASR: The Good, the Bad, the Ugly, and the Way Forward

Recent research has demonstrated that training a linear connector between speech foundation encoders and large language models (LLMs) enables this architecture to achieve strong ASR capabilities. Despite the impressive results, it remains unclear whether these simple approaches are robust enough across different scenarios and speech conditions, such as domain shifts and speech perturbations. In this paper, we address these questions by conducting various ablation experiments using a recent and widely adopted approach called SLAM-ASR. We present novel empirical findings that offer insights on how to effectively utilize the SLAM-ASR architecture across a wide range of settings. Our main findings indicate that SLAM-ASR exhibits poor performance in cross-domain evaluation settings. Additionally, speech perturbations on in-domain data, such as changes in speech rate or additive noise, can significantly degrade performance. Our findings offer critical insights for fine-tuning and configuring robust LLM-based ASR models, tailored to different data characteristics and computational resources.

cs.CL↗

arXiv2024

XLSR-Transducer: Streaming ASR for Self-Supervised Pretrained Models

Self-supervised pretrained models exhibit competitive performance in automatic speech recognition on finetuning, even with limited in-domain supervised data. However, popular pretrained models are not suitable for streaming ASR because they are trained with full attention context. In this paper, we introduce XLSR-Transducer, where the XLSR-53 model is used as encoder in transducer setup. Our experiments on the AMI dataset reveal that the XLSR-Transducer achieves 4% absolute WER improvement over Whisper large-v2 and 8% over a Zipformer transducer model trained from scratch. To enable streaming capabilities, we investigate different attention masking patterns in the self-attention computation of transformer layers within the XLSR-53 model. We validate XLSR-Transducer on AMI and 5 languages from CommonVoice under low-resource scenarios. Finally, with the introduction of attention sinks, we reduce the left context by half while achieving a relative 12% improvement in WER.

eess.AS↗

arXiv2024

TokenVerse: Towards Unifying Speech and NLP Tasks via Transducer-based ASR

In traditional conversational intelligence from speech, a cascaded pipeline is used, involving tasks such as voice activity detection, diarization, transcription, and subsequent processing with different NLP models for tasks like semantic endpointing and named entity recognition (NER). Our paper introduces TokenVerse, a single Transducer-based model designed to handle multiple tasks. This is achieved by integrating task-specific tokens into the reference text during ASR model training, streamlining the inference and eliminating the need for separate NLP models. In addition to ASR, we conduct experiments on 3 different tasks: speaker change detection, endpointing, and NER. Our experiments on a public and a private dataset show that the proposed method improves ASR by up to 7.7% in relative WER while outperforming the cascaded pipeline approach in individual task performance. Our code is publicly available: https://github.com/idiap/tokenverse-unifying-speech-nlp

cs.CL↗

arXiv2024

Fast Streaming Transducer ASR Prototyping via Knowledge Distillation with Whisper

The training of automatic speech recognition (ASR) with little to no supervised data remains an open question. In this work, we demonstrate that streaming Transformer-Transducer (TT) models can be trained from scratch in consumer and accessible GPUs in their entirety with pseudo-labeled (PL) speech from foundational speech models (FSM). This allows training a robust ASR model just in one stage and does not require large data and computational budget compared to the two-step scenario with pre-training and fine-tuning. We perform a comprehensive ablation on different aspects of PL-based streaming TT models such as the impact of (1) shallow fusion of n-gram LMs, (2) contextual biasing with named entities, (3) chunk-wise decoding for low-latency streaming applications, and (4) TT overall performance as the function of the FSM size. Our results demonstrate that TT can be trained from scratch without supervised data, even with very noisy PLs. We validate the proposed framework on 6 languages from CommonVoice and propose multiple heuristics to filter out hallucinated PLs.

cs.CL↗

arXiv2022

Improved far-field speech recognition using Joint Variational Autoencoder

Automatic Speech Recognition (ASR) systems suffer considerably when source speech is corrupted with noise or room impulse responses (RIR). Typically, speech enhancement is applied in both mismatched and matched scenario training and testing. In matched setting, acoustic model (AM) is trained on dereverberated far-field features while in mismatched setting, AM is fixed. In recent past, mapping speech features from far-field to close-talk using denoising autoencoder (DA) has been explored. In this paper, we focus on matched scenario training and show that the proposed joint VAE based mapping achieves a significant improvement over DA. Specifically, we observe an absolute improvement of 2.5% in word error rate (WER) compared to DA based enhancement and 3.96% compared to AM trained directly on far-field filterbank features.

eess.AS↗

arXiv2022

Scalable Multi-node Fast Fourier Transform on GPUs

In this paper, we present the details of our multi-node GPU-FFT library, as well its scaling on Selene HPC system. Our library employs slab decomposition for data division and MPI for communication among GPUs. We performed GPU-FFT on $1024^3$, $2048^3$, and $4096^3$ grids using a maximum of 512 A100 GPUs. We observed good scaling for $4096^3$ grid with 64 to 512 GPUs. We report that the timings of multicore FFT of $1536^3$ grid with 196608 cores of Cray XC40 is comparable to that of GPU-FFT of $2048^3$ grid with 128 GPUs. The efficiency of GPU-FFT is due to the fast computation capabilities of A100 card and efficient communication via NVlink.

physics.comp-ph↗

arXiv2021

SRIB Submission to Interspeech 2021 DiCOVA Challenge

The COVID-19 pandemic has resulted in more than 125 million infections and more than 2.7 million casualties. In this paper, we attempt to classify covid vs non-covid cough sounds using signal processing and deep learning methods. Air turbulence, the vibration of tissues, movement of fluid through airways, opening, and closure of glottis are some of the causes for the production of the acoustic sound signals during cough. Does the COVID-19 alter the acoustic characteristics of breath, cough, and speech sounds produced through the respiratory system? This is an open question waiting for answers. In this paper, we incorporated novel data augmentation methods for cough sound augmentation and multiple deep neural network architectures and methods along with handcrafted features. Our proposed system gives 14% absolute improvement in area under the curve (AUC). The proposed system is developed as part of Interspeech 2021 special sessions and challenges viz. diagnosing of COVID-19 using acoustics (DiCOVA). Our proposed method secured the 5th position on the leaderboard among 29 participants.

eess.AS↗

arXiv2015

On Optimizing Human-Machine Task Assignments

When crowdsourcing systems are used in combination with machine inference systems in the real world, they benefit the most when the machine system is deeply integrated with the crowd workers. However, if researchers wish to integrate the crowd with "off-the-shelf" machine classifiers, this deep integration is not always possible. This work explores two strategies to increase accuracy and decrease cost under this setting. First, we show that reordering tasks presented to the human can create a significant accuracy improvement. Further, we show that greedily choosing parameters to maximize machine accuracy is sub-optimal, and joint optimization of the combined system improves performance.

cs.HC↗