Anshul Wadhawan
YOU?
Author Swipe
View article: Adapting Whisper for Streaming Speech Recognition via Two-Pass Decoding
Adapting Whisper for Streaming Speech Recognition via Two-Pass Decoding Open
OpenAI Whisper is a family of robust Automatic Speech Recognition (ASR) models trained on 680,000 hours of audio. However, its encoder-decoder architecture, trained with a sequence-to-sequence objective, lacks native support for streaming …
View article: Learning When to Speak: Latency and Quality Trade-offs for Simultaneous Speech-to-Speech Translation with Offline Models
Learning When to Speak: Latency and Quality Trade-offs for Simultaneous Speech-to-Speech Translation with Offline Models Open
Recent work in speech-to-speech translation (S2ST) has focused primarily on offline settings, where the full input utterance is available before any output is given. This, however, is not reasonable in many real-world scenarios. In latency…
View article: Hopeful Men@LT-EDI-EACL2021: Hope Speech Detection Using Indic Transliteration and Transformers
Hopeful Men@LT-EDI-EACL2021: Hope Speech Detection Using Indic Transliteration and Transformers Open
This paper aims to describe the approach we used to detect hope speech in the HopeEDI dataset. We experimented with two approaches. In the first approach, we used contextual embeddings to train classifiers using logistic regression, random…
View article: AraBERT and Farasa Segmentation Based Approach For Sarcasm and Sentiment\n Detection in Arabic Tweets
AraBERT and Farasa Segmentation Based Approach For Sarcasm and Sentiment\n Detection in Arabic Tweets Open
This paper presents our strategy to tackle the EACL WANLP-2021 Shared Task 2:\nSarcasm and Sentiment Detection. One of the subtasks aims at developing a\nsystem that identifies whether a given Arabic tweet is sarcastic in nature or\nnot, w…
View article: AraBERT and Farasa Segmentation Based Approach For Sarcasm and Sentiment Detection in Arabic Tweets
AraBERT and Farasa Segmentation Based Approach For Sarcasm and Sentiment Detection in Arabic Tweets Open
This paper presents our strategy to tackle the EACL WANLP-2021 Shared Task 2: Sarcasm and Sentiment Detection. One of the subtasks aims at developing a system that identifies whether a given Arabic tweet is sarcastic in nature or not, whil…
View article: Hopeful_Men@LT-EDI-EACL2021: Hope Speech Detection Using Indic Transliteration and Transformers
Hopeful_Men@LT-EDI-EACL2021: Hope Speech Detection Using Indic Transliteration and Transformers Open
This paper aims to describe the approach we used to detect hope speech in the HopeEDI dataset. We experimented with two approaches. In the first approach, we used contextual embeddings to train classifiers using logistic regression, random…
View article: Towards Emotion Recognition in Hindi-English Code-Mixed Data: A Transformer Based Approach
Towards Emotion Recognition in Hindi-English Code-Mixed Data: A Transformer Based Approach Open
In the last few years, emotion detection in social-media text has become a popular problem due to its wide ranging application in better understanding the consumers, in psychology, in aiding human interaction with computers, designing smar…
View article: Dialect Identification in Nuanced Arabic Tweets Using Farasa Segmentation and AraBERT
Dialect Identification in Nuanced Arabic Tweets Using Farasa Segmentation and AraBERT Open
This paper presents our approach to address the EACL WANLP-2021 Shared Task 1: Nuanced Arabic Dialect Identification (NADI). The task is aimed at developing a system that identifies the geographical location(country/province) from where an…