14 citations · 24 across the 20 of their papers we have counts for
23 papers
Universal Semantic Disentangled Privacy-preserving Speech Representation Learning
Biel Tura Vecino, Subhadeep Maji, Aravind Varier +11
The use of audio recordings of human speech to train LLMs poses privacy concerns due to these models' potential to generate outputs that closely resemble artifacts in the training…
Multi-Modal Retrieval For Large Language Model Based Speech Recognition
Jari Kolehmainen, Aditya Gourav, Prashanth Gurunath Shivakumar +5
Retrieval is a widely adopted approach for improving language models leveraging external information. As the field moves towards multi-modal large language models, it is important…
Search Optimization with Query Likelihood Boosting and Two-Level Approximate Search for Edge Devices
Jianwei Zhang, Helian Feng, Xin He +3
We present a novel search optimization solution for approximate nearest neighbor (ANN) search on resource-constrained edge devices. Traditional ANN approaches fall short in meeting…
Accelerator-Aware Training for Transducer-Based Speech Recognition
Suhaila M. Shakiah, Rupak Vignesh Swaminathan, Hieu Duy Nguyen +6
Machine learning model weights and activations are represented in full-precision during training. This leads to performance degradation in runtime when deployed on neural network a…
Robust Acoustic and Semantic Contextual Biasing in Neural Transducers for Speech Recognition
Xuandi Fu, Kanthashree Mysore Sathyendra, Ankur Gandhe +4
Attention-based contextual biasing approaches have shown significant improvements in the recognition of generic and/or personal rare-words in End-to-End Automatic Speech Recognitio…
Lookahead When It Matters: Adaptive Non-causal Transformers for Streaming Neural Transducers
Grant P. Strimel, Yi Xie, Brian King +3
Streaming speech recognition architectures are employed for low-latency, real-time applications. Such architectures are often characterized by their causality. Causal architectures…
Dual-Attention Neural Transducers for Efficient Wake Word Spotting in Speech Recognition
Saumya Y. Sahai, Jing Liu, Thejaswi Muniyappa +8
We present dual-attention neural biasing, an architecture designed to boost Wake Words (WW) recognition and improve inference time latency on speech recognition tasks. This archite…
Dialog act guided contextual adapter for personalized speech recognition
Feng-Ju Chang, Thejaswi Muniyappa, Kanthashree Mysore Sathyendra +3
Personalization in multi-turn dialogs has been a long standing challenge for end-to-end automatic speech recognition (E2E ASR) models. Recent work on contextual adapters has tackle…
PROCTER: PROnunciation-aware ConTextual adaptER for personalized speech recognition in neural transducers
Rahul Pandey, Roger Ren, Qi Luo +7
End-to-End (E2E) automatic speech recognition (ASR) systems used in voice assistants often have difficulties recognizing infrequent words personalized to the user, such as names an…
Sub-8-bit quantization for on-device speech recognition: a regularization-free approach
Kai Zhen, Martin Radfar, Hieu Duy Nguyen +3
For on-device automatic speech recognition (ASR), quantization aware training (QAT) is ubiquitous to achieve the trade-off between model predictive performance and efficiency. Amon…
ConvRNN-T: Convolutional Augmented Recurrent Neural Network Transducers for Streaming Speech Recognition
Martin Radfar, Rohit Barnwal, Rupak Vignesh Swaminathan +4
The recurrent neural network transducer (RNN-T) is a prominent streaming end-to-end (E2E) ASR technology. In RNN-T, the acoustic encoder commonly consists of stacks of LSTMs. Very…
Compute Cost Amortized Transformer for Streaming ASR
Yi Xie, Jonathan Macoskey, Martin Radfar +5
We present a streaming, Transformer-based end-to-end automatic speech recognition (ASR) architecture which achieves efficient neural inference through compute cost amortization. Ou…
Latency Control for Keyword Spotting
Christin Jose, Joseph Wang, Grant P. Strimel +3
Conversational agents commonly utilize keyword spotting (KWS) to initiate voice interaction with the user. For user experience and privacy considerations, existing approaches to KW…
Contextual Adapters for Personalized Speech Recognition in Neural Transducers
Kanthashree Mysore Sathyendra, Thejaswi Muniyappa, Feng-Ju Chang +5
Personal rare word recognition in end-to-end Automatic Speech Recognition (E2E ASR) models is a challenge due to the lack of training data. A standard way to address this issue is…
A neural prosody encoder for end-ro-end dialogue act classification
Kai Wei, Dillon Knox, Martin Radfar +6
Dialogue act classification (DAC) is a critical task for spoken language understanding in dialogue systems. Prosodic features such as energy and pitch have been shown to be useful…
Multi-task RNN-T with Semantic Decoder for Streamable Spoken Language Understanding
Xuandi Fu, Feng-Ju Chang, Martin Radfar +4
End-to-end Spoken Language Understanding (E2E SLU) has attracted increasing interest due to its advantages of joint optimization and low latency when compared to traditionally casc…
Attentive Contextual Carryover for Multi-Turn End-to-End Spoken Language Understanding
Kai Wei, Thanh Tran, Feng-Ju Chang +8
Recent years have seen significant advances in end-to-end (E2E) spoken language understanding (SLU) systems, which directly predict intents and slots from spoken audio. While dialo…
Learning a Neural Diff for Speech Models
Jonathan Macoskey, Grant P. Strimel, Ariya Rastrow
As more speech processing applications execute locally on edge devices, a set of resource constraints must be considered. In this work we address one of these constraints, namely o…
Bifocal Neural ASR: Exploiting Keyword Spotting for Inference Optimization
Jonathan Macoskey, Grant P. Strimel, Ariya Rastrow
We present Bifocal RNN-T, a new variant of the Recurrent Neural Network Transducer (RNN-T) architecture designed for improved inference time latency on speech recognition tasks. Th…
Amortized Neural Networks for Low-Latency Speech Recognition
Jonathan Macoskey, Grant P. Strimel, Jinru Su +1
We introduce Amortized Neural Networks (AmNets), a compute cost- and latency-aware network architecture particularly well-suited for sequence modeling tasks. We apply AmNets to the…
CoDERT: Distilling Encoder Representations with Co-learning for Transducer-based Speech Recognition
Rupak Vignesh Swaminathan, Brian King, Grant P. Strimel +2
We propose a simple yet effective method to compress an RNN-Transducer (RNN-T) through the well-known knowledge distillation paradigm. We show that the transducer's encoder outputs…
Semantic Complexity in End-to-End Spoken Language Understanding
Joseph P. McKenna, Samridhi Choudhary, Michael Saxon +2
End-to-end spoken language understanding (SLU) models are a class of model architectures that predict semantics directly from speech. Because of their input and output types, we re…
Statistical Model Compression for Small-Footprint Natural Language Understanding
Grant P. Strimel, Kanthashree Mysore Sathyendra, Stanislav Peshterliev
In this paper we investigate statistical model compression applied to natural language understanding (NLU) models. Small-footprint NLU models are important for enabling offline sys…