Search Results for author:
Found 9 papers, 1 papers with code
Fixed-point quantization aware training for on-device keyword-spotting
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.
Conversational Text-to-SQL: An Odyssey into State-of-the-Art and Challenges Ahead
Conversational, multi-turn, text-to-SQL (CoSQL) tasks map natural language utterances in a dialogue to SQL queries.
N-Best Hypotheses Reranking for Text-To-SQL Systems
Text-to-SQL task maps natural language utterances to structured queries that can be issued to a database.
Wakeword Detection under Distribution Shifts
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.
Sub 8-Bit Quantization of Streaming Keyword Spotting Models for Embedded Chipsets
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.
Exploiting Large-scale Teacher-Student Training for On-device Acoustic Models
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.
Realizing Petabyte Scale Acoustic Modeling
We present the design and evaluation of a highly scalable and resource efficient SSL system for AM.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Lessons from Building Acoustic Models with a Million Hours of Speech
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.
Improving noise robustness of automatic speech recognition via parallel data and teacher-student learning
For real-world speech recognition applications, noise robustness is still a challenge.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
