Author

Martin Radfar

Research Scientist

Filters

Applied filters

15 results found

Sort

FANS: Fusing ASR and NLU for on-device SLU

Martin Radfar, Thanasis Mouchtaris, Siegfried Kunzmann, Ariya Rastrow

Interspeech 2021

2021

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 deploy a cascade of two neural models where the first one maps the input audio to a transcript (ASR) and the second predicts the intent and slots from the transcript (NLU). In this paper, we introduce FANS, a new end-to-end SLU

Conversational AI
Multi-channel transformer transducer for speech recognition

Feng-Ju (Claire) Chang, Martin Radfar, Thanasis Mouchtaris, Maurizio Omologo

Interspeech 2021

2021

Multi-channel inputs offer several advantages over singlechannel, to improve the robustness of on-device speech recognition systems. Recent work on multi-channel transformer, has proposed a way to incorporate such inputs into end-to-end ASR for improved accuracy. However, this approach is characterized by a high computational complexity, which prevents it from being deployed in on-device systems. In this

Conversational AI
End-to-end multi-channel transformer for speech recognition

Feng-Ju (Claire) Chang, Martin Radfar, Thanasis Mouchtaris, Brian King, Siegfried Kunzmann

ICASSP 2021

2021

Transformers are powerful neural architectures that allow integrating different modalities using attention mechanisms. In this paper, we leverage the neural transformer architectures for multi-channel speech recognition systems, where the spectral and spatial information collected from different microphones are integrated using attention layers. Our multi-channel transformer network mainly consists of three

Conversational AI
Encoding syntactic knowledge in transformer encoder for intent detection and slot filling

Jixuan Wang, Kai Wei, Martin Radfar, Weiwei Zhang, Clement Chung

AAAI 2021

2021

We propose a novel Transformer encoder-based architecture with syntactical knowledge encoded for intent detection and slot filling. Specifically, we encode syntactic knowledge into the Transformer encoder by jointly training it to predict syntactic parse ancestors and part-of-speech of each token via multi-task learning. To our knowledge, this is the first work that incorporates syntactic knowledge into

Conversational AI
End-to-end neural transformer based spoken language understanding

Martin Radfar, Thanasis Mouchtaris, Siegfried Kunzmann

Interspeech 2020

2020

Spoken language understanding (SLU) refers to the process of inferring the semantic information from audio signals. While the neural transformers consistently deliver the best performance among the state-of-the-art neural architectures in field of natural language processing (NLP), their merits in a closely related field, i.e., spoken language understanding (SLU) have not been investigated. In this paper

Conversational AI