This article aims on giving more details about Speech To Text outputs and hints on how to tailor Speech To Text to suit best your needs. In the process of transcribing speech, the Speech To Text technology usually identifies multiple alternatives for individual speech segments, as multiple phrases can have similar pronunciations, possibly with different word boundaries, e.g. “eight tea…
Search: explained
7 results
This article aims on giving more details about Keyword Spotting outputs and hints on how to tailor Keyword Spotting to suit best your needs. Scoring Keyword Spotting works by calculating likelihood ratios (LR) that at a given spot occurs a keyword or just any other speech, and comparing those two likelihood ratios. The following scheme shows Background model for anything…
…workers… explained article. server.n_task_limit # Sets limit for number of pending operations. server.n_task_limit = 1000 Sets the maximum number of “pending” tasks (see the asynchronous requests statuses in REST API documentation). This value basically sets the size of processing queue and therefore indirectly defines how quickly would the server be able to react to changes. E.g. if the server is…
…the fact that it’s set on confidence, which is recalculated from raw score using a sigmoid function. It’s strongly recommended to check details in Keyword Spotting results explained article. Keyword list example Here you can see an example of keyword list in JSON format for Speech Engine. a contract keyword, which is enabled (i.e. will be included in search), not…
…faster detection of barge-in, e.g. in voicebot application New: All 5th generation STT models now use Minimum Bayes-Risk Decoding for Confusion Network construction Confusion Network results now contain precise start- and end times for each individual alternative word New: KWS confidence value calculation can be modified using confidence_shift and confidence_sharpness values (see KWS results explained article for more details) New:…
…by server.identifier or server.logging.database.identifier configuration settings (see SPE configuration file explained for details) ProcessId numeric PID of the process which created the log record Thread identifier of thread which created the log record ThreadId numeric ID of thread which created the log record Priority priority of the operation which created the log record Text raw log text as it would…
…their priority (see Task prioritization section in REST API documentation and also Understanding SPE processing priority article); handling tasks with identical priority follows the FIFO principle. Tasks are picked up from the queue and handled by workers (which allocate instances of technologies for processing – see Speech Engine and technologies, instances, workers… explained for more details). Number of tasks which…