Customer-obsessed science
Research areas
-
November 16, 202611 min readNew open-source tool turns existing test suites into sets of formal-verification tasks, which catch buggy solutions that tests alone would miss.
-
November 11, 20265 min read
-
-
-
Featured news
-
AAAI 20212021We study the problem of batch learning from bandit feedback in the setting of extremely large action spaces. Learning from extreme bandit feedback is ubiquitous in recommendation systems, in which billions of decisions are made over sets consisting of millions of choices in a single day, yielding massive observational data. In these large-scale real-world applications, supervised learning frameworks such
-
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
-
ICASSP 20212021We present a novel online end-to-end neural diarization system, BWEDA-EEND, that processes data incrementally for a variable number of speakers. The system is based on the Encoder-Decoder-Attractor (EDA) architecture of Horiguchi et al., but utilizes the incremental Transformer encoder, attending only to its left contexts and using block-level recurrence in the hidden states to carry information from block
Collaborations
View allWhether you're a faculty member or student, there are number of ways you can engage with Amazon.
View all