-
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
-
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. -
Animation by O’Reilly Science ArtJune 06, 2019New approach to reference resolution rewrites queries to clarify ambiguous references.
-
June 05, 2019Today, customer exchanges with Alexa are generally either one-shot requests, like “Alexa, what’s the weather?”, or interactions that require multiple requests to complete more complex tasks.
-
May 21, 2019A person’s tone of voice can tell you a lot about how they’re feeling. Not surprisingly, emotion recognition is an increasingly popular conversational-AI research topic.
-
May 16, 2019Text normalization is an important process in conversational AI. If an Alexa customer says, “book me a table at 5:00 p.m.”, the automatic speech recognizer will transcribe the time as “five p m”. Before a skill can handle this request, “five p m” will need to be converted to “5:00PM”. Once Alexa has processed the request, it needs to synthesize the response — say, “Is 6:30 p.m. okay?” Here, 6:30PM will be converted to “six thirty p m” for the text-to-speech synthesizer. We call the process of converting “5:00PM” to “five p m” text normalization and its counterpart — converting “five p m” to “5:00PM” — inverse text normalization.
-
May 13, 2019Recently, we published a paper showing that training a neural network to do language processing in English, then retraining it in German, drastically reduces the amount of German-language training data required to achieve a given level of performance.
