Abstract: In general, the disclosure describes techniques for detecting synthetic speech in an audio clip. In an example, a computing system may include processing circuitry and memory for executing a machine learning system. The machine learning system may be configured to process an audio clip to generate a plurality of speech artifact embeddings based on a plurality of synthetic speech artifact features. The machine learning system may further be configured to compute one or more scores based on the plurality of speech artifact embeddings. The machine learning system may further be configured to determine, based on the one or more scores, whether one or more frames of the audio clip include synthetic speech. The machine learning system may further be configured to output an indication of whether the one or more frames of the audio clip include synthetic speech.

Abstract: In some examples, a computing system includes a storage device configured to store a machine learning model trained with audio feature values to determine a reliability of an audio segment for performing speech processing; and processing circuitry. The processing circuitry is configured to: receive an audio dataset comprising a sequence of audio segments; extract, for each audio segment of the sequence of audio segments, a set of audio feature values corresponding to a set of audio features; execute the machine learning model to determine, for each audio segment of the sequence of audio segments, a reliability score based on the set of audio feature values corresponding to the respective audio segment, wherein the reliability score indicates a reliability of the audio segment for performing speech processing; and output an indication of the respective reliability scores determined for at least one audio segment of the sequence of audio segments.