There is provided mechanisms for handling poor audio quality. A method is performed by a receiving terminal device. The method comprises obtaining an indication of poor audio quality of incoming audio at the receiving terminal device. The incoming audio originates from a transmitting terminal device. The method comprises initiating text conversion of the incoming audio. The method comprises receiving text resulting from automatic speech recognition having been applied to the incoming audio. The method comprises providing a representation of the text to a user interface of the receiving terminal device.

Disclosed is a wireless communication device including a voice recognition portion configured to convert a voice signal input through a microphone into a syllable information stream using voice recognition, an encoding portion configured to encode the syllable information stream to generate digital transmission data, a transmission portion configured to modulate from the digital transmission data to a transmission signal and transmit the transmission signal through an antenna, a reception portion configured to demodulate from a reception signal received through the antenna to a digital reception data and output the digital reception data, a decoding portion configured to decode the digital reception data to generate the syllable information stream and a voice synthesis portion configured to convert the syllable information stream into the voice signal using voice synthesis and output the voice signal through a speaker.

A system for and method of characterizing a target application acoustic domain analyzes one or more speech data samples from the target application acoustic domain to determine one or more target acoustic characteristics, including a CODEC type and bit-rate associated with the speech data samples. The determined target acoustic characteristics may also include other aspects of the target speech data samples such as sampling frequency, active bandwidth, noise level, reverberation level, clipping level, and speaking rate. The determined target acoustic characteristics are stored in a memory as a target acoustic data profile. The data profile may be used to select and/or modify one or more out of domain speech samples based on the one or more target acoustic characteristics.

A customer is detected at a drive-thru and a natural language voice dialogue session is established with the customer. The customer provides voice inquiries and order details via speech during the session, the speech is translated to text sentences, and commands are issued to a transaction system through an Application Programming Interface (API) based on the text of the sentences. The transaction system updates a display associated with the drive-thru based on the commands processed for the session and places an order for the customer with a Point-Of-Sale (POS) terminal associated with the drive-thru based on the order details.

A method of performing speech recognition using a two-pass deliberation architecture includes receiving a first-pass hypothesis and an encoded acoustic frame and encoding the first-pass hypothesis at a hypothesis encoder. The first-pass hypothesis is generated by a recurrent neural network (RNN) decoder model for the encoded acoustic frame. The method also includes generating, using a first attention mechanism attending to the encoded acoustic frame, a first context vector, and generating, using a second attention mechanism attending to the encoded first-pass hypothesis, a second context vector. The method also includes decoding the first context vector and the second context vector at a context vector decoder to form a second-pass hypothesis

A speech-synthesizing device includes a hierarchical prosodic module, a prosody-analyzing device, and a prosody-synthesizing unit. The hierarchical prosodic module generates at least a first hierarchical prosodic model. The prosody-analyzing device receives a low-level linguistic feature, a high-level linguistic feature and a first prosodic feature, and generates at least a prosodic tag based on the low-level linguistic feature, the high-level linguistic feature, the first prosodic feature and the first hierarchical prosodic model. The prosody-synthesizing unit synthesizes a second prosodic feature based on the hierarchical prosodic module, the low-level linguistic feature and the prosodic tag.

Innovations in phase quantization during speech encoding and phase reconstruction during speech decoding are described. For example, to encode a set of phase values, a speech encoder omits higher-frequency phase values and/or represents at least some of the phase values as a weighted sum of basis functions. Or, as another example, to decode a set of phase values, a speech decoder reconstructs at least some of the phase values using a weighted sum of basis functions and/or reconstructs lower-frequency phase values then uses at least some of the lower-frequency phase values to synthesize higher-frequency phase values. In many cases, the innovations improve the performance of a speech codec in low bitrate scenarios, even when encoded data is delivered over a network that suffers from insufficient bandwidth or transmission quality problems.

A method and apparatus include receiving a text input that includes a sequence of text components. Respective temporal durations of the text components are determined using a duration model. A spectrogram frame is generated based on the duration model. An audio waveform is generated based on the spectrogram frame. Video information is generated based on the audio waveform. The audio waveform is provided as an output along with a corresponding video.

A system for and method of characterizing a target application acoustic domain analyzes one or more speech data samples from the target application acoustic domain to determine one or more target acoustic characteristics, including a CODEC type and bit-rate associated with the speech data samples. The determined target acoustic characteristics may also include other aspects of the target speech data samples such as sampling frequency, active bandwidth, noise level, reverberation level, clipping level, and speaking rate. The determined target acoustic characteristics are stored in a memory as a target acoustic data profile. The data profile may be used to select and/or modify one or more out of domain speech samples based on the one or more target acoustic characteristics.

Non-verbalized tokens, such as punctuation, are automatically predicted and inserted into a transcription of speech in which the tokens were not explicitly verbalized. Token prediction may be integrated with speech decoding, rather than performed as a post-process to speech decoding.