5 citations · 11 across the 7 of their papers we have counts for
8 papers
Fixed-point quantization aware training for on-device keyword-spotting
Sashank Macha, Om Oza, Alex Escott +5
Fixed-point (FXP) inference has proven suitable for embedded devices with limited computational resources, and yet model training is continually performed in floating-point (FLP).…
Conversational Text-to-SQL: An Odyssey into State-of-the-Art and Challenges Ahead
Sree Hari Krishnan Parthasarathi, Lu Zeng, Dilek Hakkani-Tur
Conversational, multi-turn, text-to-SQL (CoSQL) tasks map natural language utterances in a dialogue to SQL queries. State-of-the-art (SOTA) systems use large, pre-trained and finet…
N-Best Hypotheses Reranking for Text-To-SQL Systems
Lu Zeng, Sree Hari Krishnan Parthasarathi, Dilek Hakkani-Tur
Text-to-SQL task maps natural language utterances to structured queries that can be issued to a database. State-of-the-art (SOTA) systems rely on finetuning large, pre-trained lang…
Wakeword Detection under Distribution Shifts
Sree Hari Krishnan Parthasarathi, Lu Zeng, Christin Jose +1
We propose a novel approach for semi-supervised learning (SSL) designed to overcome distribution shifts between training and real-world data arising in the keyword spotting (KWS) t…
Sub 8-Bit Quantization of Streaming Keyword Spotting Models for Embedded Chipsets
Lu Zeng, Sree Hari Krishnan Parthasarathi, Yuzong Liu +4
We propose a novel 2-stage sub 8-bit quantization aware training algorithm for all components of a 250K parameter feedforward, streaming, state-free keyword spotting model. For the…
Exploiting Large-scale Teacher-Student Training for On-device Acoustic Models
Jing Liu, Rupak Vignesh Swaminathan, Sree Hari Krishnan Parthasarathi +3
We present results from Alexa speech teams on semi-supervised learning (SSL) of acoustic models (AM) with experiments spanning over 3000 hours of GPU time, making our study one of…