-
2023 ISCA SPSC Symposium2023Federated Learning (FL) offers a privacy-preserving approach to model training, allowing edge devices to learn collaboratively without sharing data. Edge devices like Alexa and Siri are prospective sources of unlabeled audio data that can be tapped to learn robust audio representations. In this work, we bring Self-supervised Learning (SSL) and FL together to learn representations for Automatic Speech Recognition
-
Voice conversion for Lombard speaking style with implicit and explicit acoustic feature conditioningInterspeech 2023 Workshop on Machine Learning Challenges for Hearing Aids2023Text-to-Speech (TTS) systems in Lombard speaking style can im-prove the overall intelligibility of speech, useful for hearing loss and noisy conditions. However, training those models requires a large amount of data and the Lombard effect is challenging to record due to speaker and noise variability and tiring recording conditions. Voice conversion (VC) has been shown to be a useful augmentation technique
-
CIKM 20232023In e-commerce sites, customer questions on the product detail page express the customers’ information needs about the product. The answers to these questions often provide the necessary information. In this work, we present and address the novel task of generating product insights from community questions and answers (Q&A). These insights can be presented to customers to assist them in their shopping journey
-
SIGIR 20232023Conversation disentanglement aims to identify and group utterances from a conversation into separate threads. Existing methods in the literature primarily focus on disentangling multi-party conversations involving three or more speakers, which enables their models to explicitly or implicitly incorporate speaker-related feature signals while disentangling. Most existing models require a large amount of human
-
ACL 20232023Methods to generate text from structured data have advanced significantly in recent years, primarily due to fine-tuning of pre-trained lan-guage models on large datasets. However, such models can fail to produce output faithful to the input data, particularly on out-of-domain data. Sufficient annotated data is often not avail-able for specific domains, leading us to seek an unsupervised approach to improve
Related content
-
August 07, 2019This year, at the Association for Computational Linguistics’ Workshop on Natural-Language Processing for Conversational AI, my colleagues and I won one of two best-paper awards for our work on slot carryover. -
July 31, 2019Computerized question-answering systems usually take one of two approaches. Either they do a text search and try to infer the semantic relationships between entities named in the text, or they explore a hand-curated knowledge graph, a data structure that directly encodes relationships among entities.
-
Image: Getty ImagesJuly 22, 2019Using machine learning to train information retrieval models — such as Internet search engines — is difficult because it requires so much manually annotated data. Of course, training most machine learning systems requires manually annotated data, but because information retrieval models must handle such a wide variety of queries, they require a lot of data. Consequently, most information retrieval systems rely primarily on mechanisms other than machine learning.
-
June 27, 2019Earlier this month, Varun Sharma and Akshit Tyagi, two master’s students from the University of Massachusetts Amherst, began summer internships at Amazon, where, like many other scientists in training, they will be working on Alexa’s spoken-language-understanding systems.
-
June 13, 2019Alexa’s ability to respond to customer requests is largely the result of machine learning models trained on annotated data. The models are fed sample texts such as “Play the Prince song 1999” or “Play River by Joni Mitchell”. In each text, labels are attached to particular words — SongName for “1999” and “River”, for instance, and ArtistName for Prince and Joni Mitchell. By analyzing annotated data, the system learns to classify unannotated data on its own.
-
June 11, 2019As Alexa expands into new countries, she usually has to be trained on new languages. But sometimes, she has to be re-trained on languages she’s already learned. British English, American English, and Indian English, for instance, are different enough that for each of them, we trained a new machine learning model from scratch.
