-
ICASSP 20192019Conventional models for emotion recognition from speech signal are trained in supervised fashion using speech utterances with emotion labels. In this study we hypothesize that speech signal depends on multiple latent variables including the emotional state, age, gender, and speech content. We propose an Adversarial Autoencoder (AAE) to perform variational inference over the latent variables and reconstruct
-
Interspeech 20192019We present a neural text-to-speech system for fine-grained prosody transfer from one speaker to another. Conventional approaches for end-to-end prosody transfer typically use either fixed-dimensional or variable-length prosody embedding via a secondary attention to encode the reference signal. How-ever, when trained on a single-speaker dataset, the conventional prosody transfer systems are not robust enough
-
NAACL 20192019In this paper, we consider advancing webscale knowledge extraction and alignment by integrating OpenIE extractions in the form of (subject, predicate, object) triples with Knowledge Bases (KB). Traditional techniques from universal schema and from schema mapping fall in two extremes: either they perform instance-level inference relying on embedding for (subject, object) pairs, thus cannot handle pairs absent
-
NAACL 20192019This work explores cross-lingual transfer learning (TL) for named entity recognition, focusing on bootstrapping Japanese from English. A deep neural network model is adopted and the best combination of weights to transfer is extensively investigated. Moreover, a novel approach is presented that overcomes linguistic differences between this language pair by romanizing a portion of the Japanese input. Experiments
-
Interspeech 20192019This paper explores the potential universality of neural vocoders. We train a WaveRNN-based vocoder on 74 speakers coming from 17 languages. This vocoder is shown to be capable of generating speech of consistently good quality (98% relative mean MUSHRA when compared to natural speech) regardless of whether the input spectrogram comes from a speaker or style seen during training or from an out-of-domain
Related content
-
January 24, 2019Machine learning systems often act on “features” extracted from input data. In a natural-language-understanding system, for instance, the features might include words’ parts of speech, as assessed by an automatic syntactic parser, or whether a sentence is in the active or passive voice. -
January 22, 2019Developing a new natural-language-understanding system usually requires training it on thousands of sample utterances, which can be costly and time-consuming to collect and annotate. That’s particularly burdensome for small developers, like many who have contributed to the library of more than 70,000 third-party skills now available for Alexa.
-
Projection image adapted from Michael Horvath under the CC BY-SA 4.0 licenseJanuary 15, 2019Neural networks have been responsible for most of the top-performing AI systems of the past decade, but they tend to be big, which means they tend to be slow. That’s a problem for systems like Alexa, which depend on neural networks to process spoken requests in real time.
-
December 21, 2018In May 2018, Amazon launched Alexa’s Remember This feature, which enables customers to store “memories” (“Alexa, remember that I took Ben’s watch to the repair store”) and recall them later by asking open-ended questions (“Alexa, where is Ben’s watch?”).
-
December 18, 2018At a recent press event on Alexa's latest features, Alexa’s head scientist, Rohit Prasad, mentioned multistep requests in one shot, a capability that allows you to ask Alexa to do multiple things at once. For example, you might say, “Alexa, add bananas, peanut butter, and paper towels to my shopping list.” Alexa should intelligently figure out that “peanut butter” and “paper towels” name two items, not four, and that bananas are a separate item.
-
December 17, 2018In recent years, data representation has emerged as an important research topic within machine learning.
