8 citations · 15 across the 17 of their papers we have counts for
18 papers
End-to-end spoken language understanding using joint CTC loss and self-supervised, pretrained acoustic encoders
Jixuan Wang, Martin Radfar, Kai Wei +1
It is challenging to extract semantic meanings directly from audio signals in spoken language understanding (SLU), due to the lack of textual information. Popular end-to-end (E2E)…
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…
Leveraging Redundancy in Multiple Audio Signals for Far-Field Speech Recognition
Feng-Ju Chang, Anastasios Alexandridis, Rupak Vignesh Swaminathan +6
To achieve robust far-field automatic speech recognition (ASR), existing techniques typically employ an acoustic front end (AFE) cascaded with a neural transducer (NT) ASR model. T…
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…
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…
Context-Aware Transformer Transducer for Speech Recognition
Feng-Ju Chang, Jing Liu, Martin Radfar +4
End-to-end (E2E) automatic speech recognition (ASR) systems often have difficulty recognizing uncommon words, that appear infrequently in the training data. One promising method, t…
Speech Emotion Recognition Using Quaternion Convolutional Neural Networks
Aneesh Muppidi, Martin Radfar
Although speech recognition has become a widespread technology, inferring emotion from speech signals still remains a challenge. To address this problem, this paper proposes a quat…
FANS: Fusing ASR and NLU for on-device SLU
Martin Radfar, Athanasios Mouchtaris, Siegfried Kunzmann +1
Spoken language understanding (SLU) systems translate voice input commands to semantics which are encoded as an intent and pairs of slot tags and values. Most current SLU systems d…
Multi-Channel Transformer Transducer for Speech Recognition
Feng-Ju Chang, Martin Radfar, Athanasios Mouchtaris +1
Multi-channel inputs offer several advantages over single-channel, to improve the robustness of on-device speech recognition systems. Recent work on multi-channel transformer, has…
The Performance Evaluation of Attention-Based Neural ASR under Mixed Speech Input
Bradley He, Martin Radfar
In order to evaluate the performance of the attention based neural ASR under noisy conditions, the current trend is to present hours of various noisy speech data to the model and m…
End-to-End Multi-Channel Transformer for Speech Recognition
Feng-Ju Chang, Martin Radfar, Athanasios Mouchtaris +2
Transformers are powerful neural architectures that allow integrating different modalities using attention mechanisms. In this paper, we leverage the neural transformer architectur…
Encoding Syntactic Knowledge in Transformer Encoder for Intent Detection and Slot Filling
Jixuan Wang, Kai Wei, Martin Radfar +2
We propose a novel Transformer encoder-based architecture with syntactical knowledge encoded for intent detection and slot filling. Specifically, we encode syntactic knowledge into…
Tie Your Embeddings Down: Cross-Modal Latent Spaces for End-to-end Spoken Language Understanding
Bhuvan Agrawal, Markus Müller, Martin Radfar +3
End-to-end (E2E) spoken language understanding (SLU) systems can infer the semantics of a spoken utterance directly from an audio signal. However, training an E2E system remains a…
End-to-End Neural Transformer Based Spoken Language Understanding
Martin Radfar, Athanasios Mouchtaris, Siegfried Kunzmann
Spoken language understanding (SLU) refers to the process of inferring the semantic information from audio signals. While the neural transformers consistently deliver the best perf…
Speech Separation Using Gain-Adapted Factorial Hidden Markov Models
Martin H. Radfar, Richard M. Dansereau, Willy Wong
We present a new probabilistic graphical model which generalizes factorial hidden Markov models (FHMM) for the problem of single-channel speech separation (SCSS) in which we wish t…