Search Results for author: Sree Hari Krishnan Parthasarathi

Found 9 papers, 1 papers with code

Fixed-point quantization aware training for on-device keyword-spotting

no code implementations4 Mar 2023 Sashank Macha, Om Oza, Alex Escott, Francesco Caliva, Robbie Armitano, Santosh Kumar Cheekatmalla, Sree Hari Krishnan Parthasarathi, Yuzong Liu

Furthermore, on an in-house KWS dataset, we show that our 8-bit FXP-QAT models have a 4-6% improvement in relative false discovery rate at fixed false reject rate compared to full precision FLP models.

Keyword Spotting Quantization

Conversational Text-to-SQL: An Odyssey into State-of-the-Art and Challenges Ahead

no code implementations21 Feb 2023 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.

Text-To-SQL

N-Best Hypotheses Reranking for Text-To-SQL Systems

no code implementations19 Oct 2022 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.

Text-To-SQL

Sub 8-Bit Quantization of Streaming Keyword Spotting Models for Embedded Chipsets

no code implementations13 Jul 2022 Lu Zeng, Sree Hari Krishnan Parthasarathi, Yuzong Liu, Alex Escott, Santosh Kumar Cheekatmalla, Nikko Strom, Shiv Vitaladevuni

We organize our results in two embedded chipset settings: a) with commodity ARM NEON instruction set and 8-bit containers, we present accuracy, CPU, and memory results using sub 8-bit weights (4, 5, 8-bit) and 8-bit quantization of rest of the network; b) with off-the-shelf neural network accelerators, for a range of weight bit widths (1 and 5-bit), while presenting accuracy results, we project reduction in memory utilization.

Keyword Spotting Quantization

Wakeword Detection under Distribution Shifts

no code implementations13 Jul 2022 Sree Hari Krishnan Parthasarathi, Lu Zeng, Christin Jose, Joseph Wang

To train effectively with a mix of human and teacher labeled data, we develop a teacher labeling strategy based on confidence heuristics to reduce entropy on the label distribution from the teacher model; the data is then sampled to match the marginal distribution on the labels.

Keyword Spotting

Exploiting Large-scale Teacher-Student Training for On-device Acoustic Models

no code implementations11 Jun 2021 Jing Liu, Rupak Vignesh Swaminathan, Sree Hari Krishnan Parthasarathi, Chunchuan Lyu, Athanasios Mouchtaris, Siegfried Kunzmann

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 the largest of its kind.

Lessons from Building Acoustic Models with a Million Hours of Speech

no code implementations2 Apr 2019 Sree Hari Krishnan Parthasarathi, Nikko Strom

This is a report of our lessons learned building acoustic models from 1 Million hours of unlabeled speech, while labeled speech is restricted to 7, 000 hours.

Decoder

Cannot find the paper you are looking for? You can Submit a new open access paper.