V-Blaze and V-Cloud Online Help

Factors Affecting Accuracy

Transcription accuracy is not a single measurement, but a rather detailed analysis pertaining to several different factors that are summarized below. Voci speech scientists apply best practices to improve accuracy against many of these factors.

Domain: Voicemail, Survey, Call Center, Healthcare, Survey, etc.

Applications in which dialogue is easiest (for example, single-caller voicemail) will yield higher accuracy results than a multi-party conversation that may include overtalk. Voci builds language models specifically for these applications to maximize accuracy and speed. Refer to Language Support for more information on available language models.

Audio quality: compression, codecs, stereo vs. mono.

The noisier and more compressed the audio, the lower the accuracy. Typical telephone audio is encoded with G.711 at a rate of 64 Kbps, and Voci takes this format as a baseline. A lower encoding rate will result in lower accuracy. Recording source audio in dual channel rather than mono will typically result in higher accuracy, as much as a 10% difference. Voci always recommends dual channel. Refer to Single-Channel (Mono) Versus Channel-Separated Audio for more information.

Language model tuning

A language model may not capture specific company and product names or jargon and speech patterns for a particular domain or industry. To improve accuracy, Voci can create a specific, tuned language model for that particular client. Refer to Custom Language Modeling for more information.

Field Tuning: Substitutions

Substitution is an automatic speech recognition (ASR) feature that can automatically correct errors in transcripts. Transcription accuracy in V‑Blaze deployments can be improved using substitution rules to find and replace transcription errors with the corrected text.

Refer to the Substitutions Feature Guide for more information on substitutions.

Field Tuning: Hinting

Hints are an effective method for improving the accuracy of targeted phrases, such as those directly impacting categorization and other types of analytics. Hints are also useful for correcting frequently occurring phrases with unusual word groupings, such as those found in marketing slogans, disclaimers, and required legal statements.

Refer to the Hinting Feature Guide for more information on hinting.