-
The Web Conference 20212021Information extraction from semi-structured webpages provides valuable long-tailed facts for augmenting knowledge graph. Relational Web tables are a critical component containing additional entities and attributes of rich and diverse knowledge. However, extracting knowledge from relational tables is challenging because of sparse contextual information. Existing work linearize table cells and heavily rely
-
AAAI Workshop on Health Intelligence (W3PHIAI-21)2021Coronavirus disease (COVID-19) has been declared as a pandemic by WHO with thousands of cases being reported each day. Numerous scientific articles are being published on the disease raising the need for a service which can organize, and query them in a reliable fashion. To support this cause we present AWS CORD-19 Search (ACS), a public, COVID19 specific, neural search engine that is powered by several
-
ICASSP 20212021While there have been several contributions exploring state-of-the-art techniques for text normalization, the problem of inverse text normalization (ITN) remains relatively unexplored. The best known approaches leverage finite-state-transducer-(FST)-based models that rely on manually curated rules and are hence not scalable. We propose an efficient and robust neural solution for ITN, leveraging transformer-based
-
ICASSP 20212021Audio codecs based on discretized neural autoencoders have recently been developed and shown to provide significantly higher compression levels for comparable quality speech output. However, these models are tightly coupled with speech content, and produce unintended outputs in noisy conditions. Based on VQ-VAE autoencoders with WaveRNN decoders, we develop compressor-enhancer encoders and accompanying
-
ICASSP 20212021Recent research shows end-to-end ASR systems can recognize overlapped speech from multiple speakers. However, all published works have assumed no latency constraints during inference, which does not hold for most voice assistant interactions. This work focuses on multi-speaker speech recognition based on a recurrent neural network transducer (RNN-T) that has been shown to provide high recognition accuracy
Related content
-
September 22, 2022Research from Alexa Speech covers a range of topics related to end-to-end neural speech recognition and fairness.
-
September 15, 2022Self-supervised training, distributed training, and knowledge distillation have delivered remarkable results, but they’re just the tip of the iceberg.
-
September 14, 2022Cyclic training of speech synthesis and speech recognition models and language understanding for better speech prosody are just a few examples of cross-pollination in speech-related fields.
-
September 06, 2022Speech recognition and text-to-speech predominate, but other topics include audio watermarking, automatic dubbing, and compression.
-
September 02, 2022Method would enable customers to evaluate supporting evidence for tip reliability.
-
August 23, 2022New speech representations and self-supervised learning are two of the recent trends that most intrigue him.